Complete Project Directory
The directory preserves every upstream project and lists the 33 guide supplements separately. <abbr title="Not established from the pinned sources">?</abbr> means the pinned source did not support a conclusion. N/A means the field does not apply to that category. Archived projects remain visible and marked, because removal would hide the history behind current comparisons.
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| AgentBox <small>★ 374 · 2026-08-23</small> | Runs multiple coding agents in parallel, each in its own sandboxed VM, locally or in the cloud, from one command. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | N/A / N/A | Open source |
| cc-haha <small>★ 14,189 · 2026-08-23</small> | Local-first desktop workspace harness for Claude Code and other agents: multi-agent sessions, Git worktrees, code diffs, a skill marketplace, and chat-app access (WeChat... | Memory, Multi-agent, Typescript | Complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| claw-code-agent <small>★ 543 · 2026-08-23</small> | Python reimplementation of the Claude Code agent architecture with zero external dependencies; interactive chat, streaming, plugin runtime, nested agent delegation, cost... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Checkpoint gated / None | <abbr title="Not established from the pinned sources">?</abbr> |
| Cline <small>★ 66,707 · 2026-08-23</small> | VS Code extension whose harness is a plan-then-act loop with per-step human approval and cost transparency; the VS Code integration is the UI shell. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Step gated / Resumable | Open source |
| Codex <small>★ 114,837 · 2026-08-23</small> | OpenAI's terminal coding agent. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Resumable | Open source |
| crush <small>★ 27,601 · 2026-08-23</small> | Charm's terminal coding agent (Charm's fork of the original OpenCode). | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Resumable | Restricted (fsl-1.1-mit) |
| DeepSeek-Reasonix <small>★ 35,065 · 2026-08-23</small> | DeepSeek-native terminal coding agent. | CLI, Memory, TUI, Typescript | Slightly complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| eigent <small>★ 15,083 · 2026-08-23</small> | Open-source desktop harness positioned as a local, free alternative to Claude Cowork and Codex: multi-agent workspace orchestration in a self-hosted app rather than a hosted... | Local, Multi-agent | Complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| Gemini CLI <small>★ 106,626 · 2026-08-23</small> | Google's first-party terminal agent for Gemini. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Resumable | Open source |
| goose <small>★ 53,295 · 2026-08-23</small> | Block-originated Rust agent, now stewarded by the Linux Foundation's Agentic AI Foundation (aaif-goose/goose). | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Headless / Resumable | Open source |
| jcode <small>★ 18,308 · 2026-08-23</small> | Rust terminal coding agent pitched as the most RAM-efficient harness in its class; MCP support, multi-provider (Claude/OpenAI). | CLI, Mcp, Memory, Provider-agnostic | Slightly complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| Kilo Code <small>★ 26,978 · 2026-08-23</small> | VS Code extension and CLI in the Cline/Roo-Code lineage : a natural pick now that Roo-Code is archived upstream. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Step gated / Resumable | <abbr title="Not established from the pinned sources">?</abbr> |
| oh-my-pi <small>★ 26,658 · 2026-08-23</small> | Terminal coding agent (fork of Pi) that wires the IDE into the harness: hash-anchored edits, a 32-tool loop tuned per-model, LSP rename/references/diagnostics on every write, a... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Resumable | Open source |
| Open Interpreter <small>★ 68,121 · 2026-08-23</small> | Lightweight terminal coding agent oriented to open models (DeepSeek, Kimi, Qwen). | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | Bounded / Resumable | Open source |
| opencode <small>★ 200,557 · 2026-08-23</small> | Open-source terminal coding agent (formerly sst/opencode; transferred to anomalyco). | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Headless / Resumable | Open source |
| OpenHands <small>★ 84,844 · 2026-08-23</small> | Dockerized software-engineering agent. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Restricted ((multi-license)) |
| pi <small>★ 95,747 · 2026-08-23</small> | The upstream AI agent toolkit behind this list's oh-my-pi fork: a unified multi-provider LLM API, agent loop, and TUI shell providing the harness that oh-my-pi's Rust rewrite... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Resumable | <abbr title="Not established from the pinned sources">?</abbr> |
| Proliferate <small>★ 310 · 2026-08-23</small> | Open-source AI IDE for Claude Code, Codex, OpenCode, and more. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Resumable | Open source |
| qwen-code <small>★ 27,310 · 2026-08-23</small> | Alibaba's official terminal coding agent, forked from Gemini CLI's agent loop and retuned for Qwen models. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Resumable | <abbr title="Not established from the pinned sources">?</abbr> |
| Roo Code <small>★ 24,326 · 2026-08-23</small> | VS Code/Cursor extension in the Cline lineage. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Step gated / Resumable | Open source |
| Symphony <small>★ 26,812 · 2026-08-23</small> | OpenAI's harness for fanning a task out into many isolated, autonomous coding-agent implementation runs and surfacing the ones that pass, so a team manages outcomes instead of... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | <abbr title="Not established from the pinned sources">?</abbr> |
| vibe-kanban <small>★ 27,893 · 2026-08-23</small> | Kanban-style fleet manager for running Claude Code, Codex, or any coding agent across many tasks at once. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| addyosmani/agent-skills <small>★ 89,221 · 2026-08-23</small> | Addy Osmani's production-grade skill pack: 24 engineering skills and 4 specialist agent personas that encode senior-dev workflows (spec through deploy) across 70+ coding agents... | IDE, Workflow | Mostly simple | N/A / N/A | Open source |
| agents-cli <small>★ 5,708 · 2026-08-23</small> | Google's official CLI and skill pack that layers agent-creation, evaluation, and deployment skills on top of whatever coding assistant you already run, rather than shipping its... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| Anthropic Skills <small>★ 171,127 · 2026-08-23</small> | Anthropic's official Agent Skills repository: SKILL.md-based folders (instructions, scripts, resources) Claude dynamically loads on Claude Code, Claude.ai, and the API. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | N/A / N/A | Restricted (anthropic terms) |
| AutoHarness <small>★ 368 · 2026-08-23</small> | Lightweight governance harness: wraps any LLM client in ~2 lines for automated harness engineering: 6-14 step pipeline, YAML constitution, risk-pattern matching, session... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Super simple | Bounded / None | Open source |
| awesome-claude-code <small>★ 52,857 · 2026-08-23</small> | Large community-curated index of Claude Code skills, slash commands, status lines, and plugins: resources for extending the harness, not a harness itself, but the most-followed... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Super simple | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| Claude Agent SDK <small>★ 7,957 · 2026-08-23</small> | Official Anthropic SDK (Python + TypeScript, demos, quickstarts): built-in tools, MCP, long-running coding agents with session bridging. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Open source |
| get-shit-done <small>★ 8,617 · 2026-08-23</small> | Goal-backward planning and wave-based execution over fresh context windows; avoids context rot by design. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | Bounded / Resumable | Open source |
| GStack <small>★ 129,281 · 2026-08-23</small> | Garry Tan's Claude Code skill stack: 23 slash-command modes (CEO/eng/design review, QA, ship, browse, retro, …) that structure one assistant as a virtual engineering team. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | N/A / N/A | Open source |
| LoopTroop <small>★ 123 · 2026-08-23</small> | Config layer that chains LLM councils for planning, Ralph loops for iterative refinement, and OpenCode worktrees for shipping. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | Bounded / Retry | Open source |
| Meta-Harness <small>★ 1,448 · 2026-08-23</small> | Reference implementation from the Meta-Harness paper: an academic testbed for harness-engineering research, not a product: useful as a citation-grade baseline rather than... | <abbr title="Not established from the pinned sources">?</abbr> | Slightly complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| planning-with-files <small>★ 26,305 · 2026-08-23</small> | Skill for persistent, file-based planning across long-running coding-agent sessions: crash-proof markdown plans, session recovery after /clear/compaction, and a deterministic... | Memory | Mostly simple | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| pmstack <small>★ 8 · 2026-08-23</small> | Claude Code config for AI product managers: CLAUDE.md plus skills for competitive analysis, PRD-from-signal, metric frameworks, stakeholder briefs, and agent eval design. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Super simple | N/A / N/A | Open source |
| RepoMaster <small>★ 543 · 2026-08-23</small> | Repo-scoped research harness: builds function-call and module-dependency graphs to explore only what's needed; large relative gains on MLE-bench and GitTaskBench with lower... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Headless / None | <abbr title="Not established from the pinned sources">?</abbr> |
| skillhub <small>★ 4,891 · 2026-08-23</small> | iFlytek's self-hosted registry for publishing, versioning, and governing agent skill packages: the harness config layer treated as an enterprise artifact store rather than a... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| superpowers <small>★ 276,518 · 2026-08-23</small> | Performance-oriented harness pack for Claude Code and 13 other harnesses (Codex, Cursor, OpenCode, Gemini CLI, more): skills, instincts, memory, security, research-first workflows. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | N/A / N/A | Open source |
| SWE-agent <small>★ 20,112 · 2026-08-23</small> | LM-driven harness built for SWE-bench: edit state, command execution, and issue-focused loop: the reference agent stack next to the benchmark itself. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Headless / Resumable | Open source |
| wshobson/agents <small>★ 39,042 · 2026-08-23</small> | Cross-harness marketplace of drop-in subagents and skills for Claude Code, Codex CLI, Cursor, OpenCode, and Copilot; specialized, production-ready agent definitions you install... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Super simple | N/A / N/A | Open source |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| AgencyBench <small>★ 94 · 2026-08-23</small> | Long-horizon agent benchmark: 32 scenarios, 138 tasks, ~1M tokens and ~90 tool calls; Docker sandbox and rubric-based + LLM judges. | Evals, Python, Sandbox | Complex | Headless / None | Open source |
| Agent Lightning <small>★ 17,609 · 2026-08-23</small> | Microsoft's training-oriented harness: optimization loops for agent behavior: when you need to improve policies over rollouts, not only score a fixed prompt. | Evals, Python, Training | Complex | Headless / Resumable | Open source |
| agent-qa <small>★ 936 · 2026-08-23</small> | Self-improving QA harness for web and mobile apps: natural-language tests, memory-backed self-healing, dashboard/CLI, MCP and skills support, plus sandboxed hooks for... | CLI, Mcp, Memory, Sandbox | Slightly complex | Headless / Retry | Restricted (fsl-1.1-alv2) |
| AgentBench <small>★ 3,682 · 2026-08-23</small> | ICLR'24 benchmark: agents across AlfWorld, DB, knowledge graphs, OS, webshop; Docker Compose, function-calling interface. | Evals, Python, Rag, Sandbox | Complex | Headless / None | Open source |
| ARC-AGI-2 <small>★ 734 · 2026-08-23</small> | ARC Prize task set: grid-based abstraction/reasoning; public and private splits for generalization. | <abbr title="Not established from the pinned sources">?</abbr> | Super simple | N/A / N/A | Open source |
| arc-agi-benchmarking <small>★ 363 · 2026-08-23</small> | Runner for ARC-AGI: multi-provider (OpenAI, Anthropic, Gemini, etc.), rate limits, retries, and scoring. | Evals, Provider-agnostic, Python | Mostly simple | Headless / Retry | Open source |
| inspect_ai <small>★ 2,606 · 2026-08-23</small> | Inspect AI core: composable eval tasks, sandboxes, scorers, and multi-model runs; the framework behind inspect_evals, not just the task bundle. | Evals, Python, Sandbox | Complex | Headless / Resumable | Open source |
| inspect_evals <small>★ 639 · 2026-08-23</small> | UK AISI/Arcadia/Vector: GAIA and other evals in Inspect AI; level 1-3, sandboxed, tool-calling solvers. | Evals, Sandbox | Slightly complex | Headless / Resumable | Open source |
| letta-evals <small>★ 83 · 2026-08-23</small> | Eval harness for stateful Letta agents; configurable suites and grading (LLM or rule-based) so you can measure what you ship. | Memory, Python | Mostly simple | Headless / None | Open source |
| SUPER <small>★ 58 · 2026-08-23</small> | Agents that set up and run ML/NLP from GitHub repos; 45 expert problems, 152 masked tasks, 602 AutoGen tasks; Docker-based. | Python, Sandbox | Slightly complex | Headless / None | Open source |
| SWE-bench <small>★ 5,691 · 2026-08-23</small> | LMs resolve real GitHub issues; Docker harness, instance IDs; standard for code-agent evals. | Evals, Python, Sandbox | Slightly complex | Headless / Resumable | Open source |
| SWE-Gym <small>★ 723 · 2026-08-23</small> | Training and evaluation for SWE agents and verifiers (ICML 2025). | Evals, Python, Training | Slightly complex | Headless / None | Open source |
| swe-smith <small>★ 748 · 2026-08-23</small> | Data generation for SWE agents; 50k+ instances across 128 repos; used for SWE-agent-LM training. | Python, Training | Slightly complex | Headless / None | Open source |
| Terminal-Bench <small>★ 533 · 2026-08-23</small> | The terminal-task benchmark coding agents now cite next to SWE-bench: hard, containerized terminal tasks scored end to end. | CLI, Evals, Python | Slightly complex | Headless / None | Open source |
| TRAIL <small>★ 22 · 2026-08-23</small> | Trace reasoning and agentic issue localization; 148 long-context traces, 841 errors, 20+ error types; Hugging Face dataset. | <abbr title="Not established from the pinned sources">?</abbr> | Mostly simple | N/A / N/A | Open source |
| VitaBench <small>★ 164 · 2026-08-23</small> | ICLR'26: 66 tools, real-world apps (delivery, travel, retail); 100 cross-scenario + 300 single-scenario tasks; adopted by Qwen/Seed. | <abbr title="Not established from the pinned sources">?</abbr> | Complex | Headless / None | Open source |
| WebArena <small>★ 1,584 · 2026-08-23</small> | Realistic web env (e.g. | Python | Complex | Headless / None | Open source |
| WebVoyager <small>★ 1,122 · 2026-08-23</small> | End-to-end web agent with LMMs: screenshots + actions on real sites; benchmark on 15 sites, GPT-4V for automatic eval. | Evals, Vision | Slightly complex | Headless / None | Open source |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| agent-squad <small>★ 7,742 · 2026-08-23</small> | AWS-originated orchestrator (now under 2FastLabs): intent classification, streaming, SupervisorAgent; "agent-as-tools" so one agent delegates to a squad. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Resumable | Open source |
| AgentSilex <small>★ 454 · 2026-08-23</small> | ~300 lines of readable agent code on top of LiteLLM; the "I want to see the whole loop" option for learning or minimal production. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Super simple | Bounded / None | Open source |
| AgentStack <small>★ 2,185 · 2026-08-23</small> | Scaffolds full agent projects; plugs in CrewAI, LangGraph, OpenAI Swarm, LlamaStack and wires AgentOps observability from day one. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | N/A / N/A | Open source |
| AgentVerse <small>★ 5,113 · 2026-08-23</small> | Task-solving and simulation envs for multi-LLM agents; deploy many agents in custom environments without building infra from scratch. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / None | Open source |
| agno <small>★ 41,848 · 2026-08-23</small> | Python agents with memory, knowledge bases, tools, and structured outputs; continues the PhiData-era product line under the Agno name: production apps, evals, and pipelines. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Resumable | Open source |
| AutoGPT <small>★ 186,806 · 2026-08-23</small> | The original autonomous loop: goal in, agent iterates with tools and memory; Forge is the dev framework, Benchmark the eval harness. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Restricted (polyform-su) |
| Bee Agent Framework <small>★ 3,383 · 2026-08-23</small> | Python + TypeScript, LF AI-backed; MCP/ACP, workflows, Requirement Agent; the one that pushes "production multi-agent" without LangChain. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Resumable | Open source |
| botpress <small>★ 14,876 · 2026-08-23</small> | Visual bot builder and runtime; multi-channel, open-source alternative to commercial bot platforms. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Open source |
| browser-use <small>★ 110,219 · 2026-08-23</small> | Python web-agent harness: natural-language goals become browser actions, driven directly over the Chrome DevTools Protocol (it dropped Playwright in August 2025). | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Retry | Open source |
| Dify <small>★ 153,269 · 2026-08-23</small> | One-stop LLM app platform: visual workflows, RAG pipeline, 50+ tools, model management; "ship from prototype to prod" in a single UI. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Retry | Restricted (fair-code) |
| Google ADK <small>★ 21,234 · 2026-08-23</small> | Google's official Agent Development Kit: code-first Python toolkit for building, evaluating, and deploying agents. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Open source |
| Haystack <small>★ 26,293 · 2026-08-23</small> | Open-source orchestration framework for context-engineered LLM apps: modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and... | Memory, Python, Rag | Complex | N/A / N/A | Open source |
| langchain <small>★ 144,822 · 2026-08-23</small> | Chains, tools, retrievers, and agents; the usual entry point for "add tools to an LLM" in Python/JS. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Retry | Open source |
| langflow <small>★ 153,582 · 2026-08-23</small> | Low-code UI to build and deploy LangChain/LangGraph flows; visual DAG editor and one-click run. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Retry | Open source |
| langgraph <small>★ 40,276 · 2026-08-23</small> | State-machine graphs over LLM steps; checkpointing, human-in-the-loop, and durable execution so workflows survive restarts. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Headless / Durable | Open source |
| letta <small>★ 24,360 · 2026-08-23</small> | Python agent runtime with tool use and control flow; lean API; stateful agents with long-horizon memory. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | Headless / Durable | Open source |
| llama-index <small>★ 51,815 · 2026-08-23</small> | Data-centric: indexing, RAG, and query engines; agent abstractions sit on top of your data pipelines. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Retry | Open source |
| mastra <small>★ 27,375 · 2026-08-23</small> | TypeScript-first; agents, tools, and workflows with a single runtime and minimal boilerplate. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Durable | Restricted (elastic-2.0) |
| n8n <small>★ 202,069 · 2026-08-23</small> | Fair-code workflow engine with 400+ nodes and native AI nodes; the self-hosted Zapier that actually does agents and LangChain. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Durable | Restricted (fair-code) |
| R2R <small>★ 7,973 · 2026-08-23</small> | RAG-first: hybrid search, knowledge graphs, multimodal; the framework for "production RAG" when you care more about retrieval than chat UI. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Retry | Open source |
| rasa <small>★ 21,302 · 2026-08-23</small> | Conversational AI stack (NLU, dialogue, actions); long-standing OSS choice for chat and voice bots. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Open source |
| semantic-kernel <small>★ 28,481 · 2026-08-23</small> | Microsoft's plugin and planner layer for LLMs; C#, Python, Java; strong on enterprise auth and orchestration. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Retry | Open source |
| Stagehand <small>★ 24,023 · 2026-08-23</small> | Browserbase's SDK for browser agents: natural-language actions (act, extract, observe) and deterministic Playwright code mix in one script, so agent flexibility and repeatable... | Browser, Typescript | Slightly complex | Bounded / None | Open source |
| SuperAgentX <small>★ 203 · 2026-08-23</small> | Lightweight multi-agent orchestrator with an AGI-angle; minimal surface, docs-first, for teams that want orchestration without the kitchen sink. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | Bounded / None | Open source |
| youtu-agent <small>★ 4,601 · 2026-08-23</small> | Tencent Cloud's agent framework: a minimal tool-calling harness designed to perform well with open-source models, positioned as a lighter alternative to heavier orchestration... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | Bounded / Retry | <abbr title="Not established from the pinned sources">?</abbr> |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| Agent Sandbox <small>★ 3,591 · 2026-08-23</small> | Kubernetes-native sandbox primitive for agent runtimes: a Sandbox resource plus warm pools and claims for fast-start, isolated, stateful workloads. | Local, Memory, Sandbox | Slightly complex | N/A / N/A | Open source |
| Cloudflare Agents <small>★ 5,478 · 2026-08-23</small> | Persistent, stateful agents on Durable Objects: state, websockets, scheduling, and AI chat baked in. | Memory, Typescript | Slightly complex | Headless / Durable | Open source |
| Community-curated agent lists <small>★ 15 · 2026-08-23</small> | Broader directories: e.g. | <abbr title="Not established from the pinned sources">?</abbr> | Super simple | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| Composio <small>★ 29,840 · 2026-08-23</small> | 1,000+ toolkits with auth, tool search, and a sandboxed workbench: drop-in tool layer so agents stop reinventing OAuth + integrations. | Python, Sandbox, Tool-discovery, Typescript | Complex | N/A / N/A | Open source |
| Daytona <small>★ 71,914 · 2026-08-23</small> | Elastic dev environments for AI-generated code: workspaces, Git, previews: infra harness between "the model wrote a patch" and "it ran in a real machine." ⚠️ Public repo... | Sandbox | Slightly complex | N/A / N/A | Open source |
| deepagents <small>★ 28,172 · 2026-08-23</small> | LangChain's Python+TypeScript agent harness on top of LangGraph: planning tool, virtual filesystem, shell sandbox, sub-agent spawning: the "Claude Code-style" harness as a... | Multi-agent, Python, Sandbox, Typescript | Slightly complex | Bounded / Durable | Open source |
| E2B <small>★ 13,523 · 2026-08-23</small> | Firecracker sandboxes for executing agent-generated code; the hosted isolation layer many tool-calling demos use instead of running arbitrary LLM output on your laptop. | Python, Sandbox | Slightly complex | N/A / N/A | Open source |
| LiteLLM <small>★ 57,066 · 2026-08-23</small> | One interface to 100+ LLMs; routing, caching, budgets. | Provider-agnostic, Python | Mostly simple | N/A / Retry | Open source |
| open-harness <small>★ 599 · 2026-08-23</small> | TypeScript Agent class on Vercel AI SDK; streaming events, filesystem/bash tools, MCP, and subagent delegation. | Mcp, Multi-agent, Typescript | Slightly complex | Bounded / None | Open source |
| openai-agents-js <small>★ 3,685 · 2026-08-23</small> | Official OpenAI Agents SDK for Node/TS: handoffs, guardrails, voice; the JS counterpart to openai-agents-python. | Multi-agent, Typescript, Voice | Slightly complex | Bounded / Resumable | Open source |
| pydantic-ai <small>★ 19,453 · 2026-08-23</small> | Type-safe Python agents with Pydantic I/O; multi-provider, MCP, Logfire observability, and human-in-the-loop. | Mcp, Provider-agnostic, Python, Typed | Slightly complex | Bounded / Durable | Open source |
| smolagents <small>★ 28,938 · 2026-08-23</small> | Code-as-action agents: model outputs Python executed in sandbox (E2B, Modal, etc.); ~1k LOC core. | Python, Sandbox | Mostly simple | Bounded / None | Open source |
| Steel <small>★ 7,529 · 2026-08-23</small> | Open-source browser API for agents: cloud or self-hosted Chrome sessions with stealth, residential proxies, CAPTCHA solving, and persistent profiles. | Browser, Local, Memory | Slightly complex | N/A / N/A | Open source |
| strands-agents <small>★ 6,984 · 2026-08-23</small> | Model-driven Python SDK; decorators for tools, native MCP, multi-agent; "minimal code" without sacrificing provider choice. | Mcp, Multi-agent, Python, Typed | Mostly simple | Bounded / Resumable | Open source |
| vercel/ai <small>★ 26,368 · 2026-08-23</small> | React and Node SDK for streaming, tool calls, and agent-style UIs; provider-agnostic. | Provider-agnostic, Typescript | Slightly complex | Bounded / Retry | Open source |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| beads <small>★ 26,534 · 2026-08-23</small> | Portable persistent-memory layer for coding agents: tracks decisions and task state outside the harness's own context window so it survives session resets and model swaps. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| claude-mem <small>★ 91,578 · 2026-08-23</small> | Session-memory plugin for Claude Code, Codex, OpenClaw, Gemini, Copilot, and more: captures everything an agent does during a session, AI-compresses it, and injects the... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | N/A / N/A | Open source |
| cognee <small>★ 30,194 · 2026-08-23</small> | Open-source memory layer for agents: an extract-cognify-load pipeline that turns your data into a queryable knowledge graph plus vector store, so agents recall facts and... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | N/A / N/A | Open source |
| Graphiti (Zep) <small>★ 30,212 · 2026-08-23</small> | Zep's open-source memory engine: real-time temporal knowledge graphs that track how facts about users and entities change over time, so agents can answer "what was true when."... | Memory, Python, Rag, Workflow | Slightly complex | N/A / N/A | Open source |
| Mem0 <small>★ 63,868 · 2026-08-23</small> | Universal memory layer for AI agents: stores user/org/session memory, retrieves on demand. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | N/A / N/A | Open source |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| AG2 <small>★ 4,883 · 2026-08-23</small> | AG2 (formerly AutoGen): the community-governed continuation of the original AutoGen project after Microsoft's fork diverged: conversable multi-agent groups, code execution, and... | Multi-agent, Python | Complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| AgentRL <small>★ 347 · 2026-08-23</small> | Multitask, multiturn RL for LLM agents; Ray-based scaling, rollout/actor workers: for teams that want to train agents, not just run them. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Open source |
| autogen <small>★ 60,585 · 2026-08-23</small> | Conversable agents and group chats; code execution and human-in-the-loop; Microsoft origin, AG2 ecosystem. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Resumable | Open source |
| ChatDev <small>★ 34,103 · 2026-08-23</small> | Multi-agent software-company simulation (CEO, CTO, programmer, tester) built on chat chains with communicative dehallucination; ChatDev 2.0 continues the line. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Headless / None | Open source |
| crewAI <small>★ 57,501 · 2026-08-23</small> | Role-based agents (roles, goals, backstories) in Crews; Flows add event-driven and hierarchical control for production. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Resumable | Open source |
| hive <small>★ 10,949 · 2026-08-23</small> | Self-hosted multi-agent harness aimed at production workloads: human-in-the-loop checkpoints and a self-improving agent loop, distinct from single-session coding-agent shells. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Resumable | <abbr title="Not established from the pinned sources">?</abbr> |
| MetaGPT <small>★ 69,962 · 2026-08-23</small> | The "AI software company" multi-agent framework: role-played PM, architect, and engineer agents turn a one-line requirement into specs, designs, and code along an SOP assembly... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Open source |
| Microsoft Agent Framework <small>★ 13,060 · 2026-08-23</small> | Microsoft's convergence of AutoGen and Semantic Kernel: build, orchestrate, and deploy agents and multi-agent workflows in Python and .NET, with graph-based workflows and... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Resumable | Open source |
| omnigent <small>★ 9,189 · 2026-08-23</small> | Open-source meta-harness: orchestrates Claude Code, Codex, Cursor, Pi, and custom agents behind one policy/sandboxing layer so teams swap harnesses without rewriting workflows. | IDE, Python, Sandbox | Complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| openai-agents-python <small>★ 28,887 · 2026-08-23</small> | Handoffs, guardrails, and multi-LLM routing; minimal surface so you own the loop. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | Bounded / Resumable | Open source |
| OpenManus <small>★ 58,048 · 2026-08-23</small> | Open, invite-free general agent from the MetaGPT team: planning plus tool use over a multi-agent loop, aimed at reproducing Manus-style autonomous task completion on your own keys. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / None | Open source |
| PraisonAI <small>★ 8,947 · 2026-08-23</small> | Autonomous multi-agent teams with a single entry point; emphasis on minimal config. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | Bounded / None | Open source |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| Arize Phoenix <small>★ 11,148 · 2026-08-23</small> | Arize's source-available, local-first tracing and eval layer: run it on your laptop or your own infra, and graduate to the managed Arize AX platform only when you need it. | Evals, Python | Slightly complex | N/A / N/A | Restricted (elastic-2.0) |
| Langfuse <small>★ 33,575 · 2026-08-23</small> | Open-source LLM engineering platform: full-trace observability, online and offline evals, prompt management, and cost metrics for agent runs in production: the monitoring layer... | Evals, Typescript | Slightly complex | N/A / N/A | Open source |
| MLflow <small>★ 27,630 · 2026-08-23</small> | Mature ML platform now covering GenAI: MLflow Tracing captures every agent step, tool call, and token, with built-in LLM evals and prompt versioning: observability for teams... | Evals, Python | Complex | N/A / N/A | Open source |
| Opik <small>★ 21,549 · 2026-08-23</small> | Comet's open-source agent observability and evaluation platform: tracing, scoring, and experiment comparison with the whole core feature set free to self-host under Apache-2.0. | Evals, Python | Slightly complex | N/A / N/A | Open source |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| Agent Zero <small>★ 18,943 · 2026-08-23</small> | Organic, prompt-defined personal agent framework: hierarchical sub-agents, persistent memory, browser and code tools, and self-modifying behavior; runs in Docker with a web UI. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Resumable | <abbr title="Not established from the pinned sources">?</abbr> |
| AIlice <small>★ 1,411 · 2026-08-23</small> | Fully autonomous general-purpose agent; one binary, Docker-ready, for when you want "set goal and walk away" without a framework. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / None | Open source |
| CowAgent <small>★ 46,642 · 2026-08-23</small> | Self-hosted harness (formerly chatgpt-on-wechat) that plans tasks, runs tools/skills, and self-evolves via memory; multi-model, multi-channel (WeChat, Telegram, etc.), one-line... | Memory, Python | Slightly complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| Eliza <small>★ 19,137 · 2026-08-23</small> | Open "agentic operating system" (elizaOS): persistent multi-agent runtime with character files, a plugin ecosystem, and social/platform integrations : the harness behind a... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Open source |
| Hermes <small>★ 234,688 · 2026-08-23</small> | Nous Research's self-improving agent: a learning loop turns experience into reusable skills, builds a persistent user model across sessions, and checkpoints state to disk with... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Headless / Resumable | Open source |
| Khoj <small>★ 36,674 · 2026-08-23</small> | Self-hostable "AI second brain": answers over your docs and the web, custom agents, scheduled automations, and multi-client reach (web, Obsidian, Emacs, WhatsApp). | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Open source |
| nanobot <small>★ 47,301 · 2026-08-23</small> | Ultra-lightweight, self-hosted personal agent framework: the harness is a Python daemon wiring tools, memory, and MCP into chat/webhook front ends (Telegram, Discord, web)... | Local, Mcp, Memory, Python | Mostly simple | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| OpenClaw <small>★ 387,220 · 2026-08-23</small> | Self-hosted, always-on personal agent (formerly Clawdbot/Moltbot): a gateway + event-loop runtime that treats messages, heartbeats, crons, and webhooks as one input queue... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Open source |
| OpenHarness (HKUDS) <small>★ 15,492 · 2026-08-23</small> | Open agent harness with a built-in personal agent ("Ohmo") that runs across Feishu, Slack, Telegram, and Discord; core tool-use, skills, memory, multi-agent coordination with... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Resumable | Open source |
| Talon <small>★ 71 · 2026-08-23</small> | Multi-platform personal agent living in Telegram, Discord, Teams, and the terminal. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Headless / Resumable | Open source |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| Agent Governance Toolkit <small>★ 6,091 · 2026-08-23</small> | Microsoft's policy-enforcement layer for autonomous agents: zero-trust identity, execution sandboxing, and OWASP Agentic Top-10 coverage sit in front of the agent loop as a... | Python, Sandbox | Slightly complex | N/A / N/A | Open source |
| agent-vault <small>★ 2,124 · 2026-08-23</small> | Infisical's HTTP credential proxy that fronts secrets for Claude Code, OpenClaw, and other agent harnesses so the agent's tool calls never see raw credentials: a harness... | <abbr title="Not established from the pinned sources">?</abbr> | Mostly simple | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| agentlog <small>★ 1 · 2026-08-23</small> | Persistent decision memory for any project: remember, recall, reflect. | CLI, Memory, Python | Super simple | N/A / N/A | Open source |
| aider <small>★ 48,420 · 2026-08-23</small> | Git-aware CLI pair programmer; edits in-repo, supports multiple models and MCP so agents see version control and tools. | CLI, Mcp, Python | Slightly complex | Checkpoint gated / Resumable | Open source |
| Better-OpenCodeMCP <small>★ 9 · 2026-08-23</small> | MCP server for OpenCode/Crush: async task execution, model bridging (e.g. | Mcp, Typescript | Mostly simple | N/A / N/A | Open source |
| chrome-devtools-mcp <small>★ 49,601 · 2026-08-23</small> | Google's official Chrome DevTools MCP server: exposes console, network, and performance-trace inspection as tool calls agents can drive directly, instead of a human clicking... | Browser, Mcp, Typescript | Mostly simple | N/A / N/A | Open source |
| cocoindex-code <small>★ 2,670 · 2026-08-23</small> | Embedded, tree-sitter/AST-based code-search CLI and MCP server that gives coding agents fast semantic lookups over a repo instead of grepping or re-reading whole files into... | CLI, Mcp | Mostly simple | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| Context7 <small>★ 61,104 · 2026-08-23</small> | MCP server that injects up-to-date, version-specific library docs into an agent's context on demand; kills the stale-training-data hallucinations that plague codegen. | Mcp, Training, Typescript | Super simple | N/A / N/A | Open source |
| continue <small>★ 35,601 · 2026-08-23</small> | Open-source IDE extension (VS Code, JetBrains); in-editor completion and chat with local or API models. | IDE, Typescript | Complex | Checkpoint gated / Resumable | Open source |
| Docker MCP Gateway <small>★ 1,537 · 2026-08-23</small> | Docker's official MCP CLI plugin / gateway; container-aware MCP tooling from Docker (replaces deprecated docker/mcp-servers path). | CLI, Mcp, Sandbox | Slightly complex | N/A / N/A | Open source |
| github-mcp-server <small>★ 32,440 · 2026-08-23</small> | GitHub's official MCP server (Go): repos, issues, PRs, code search, Actions. | Mcp | Slightly complex | N/A / N/A | Open source |
| MCP Inspector <small>★ 10,730 · 2026-08-23</small> | GUI to test and debug MCP servers; inspect tools, resources, and prompts. | Mcp, Typescript | Super simple | N/A / N/A | Open source |
| MCP Python SDK <small>★ 24,090 · 2026-08-23</small> | Official SDK to build and consume MCP servers/clients in Python; stdio and SSE transports. | Mcp, Python | Mostly simple | N/A / N/A | Open source |
| MCP Registry <small>★ 7,185 · 2026-08-23</small> | Official, community-driven registry for MCP servers: the "app store" MCP clients use to discover servers. | Mcp | Slightly complex | N/A / N/A | Open source |
| MCP Servers <small>★ 89,798 · 2026-08-23</small> | The official reference collection of Model Context Protocol servers (filesystem, git, fetch, memory, time, and more): the canonical, vetted toolset agents connect to, and the... | Mcp, Memory, Typescript | Mostly simple | N/A / N/A | Open source |
| MCP TypeScript SDK <small>★ 13,230 · 2026-08-23</small> | Official MCP implementation for Node/TS; reference for the protocol. | Mcp, Typescript | Mostly simple | N/A / N/A | Open source |
| mcp-context-forge <small>★ 4,350 · 2026-08-23</small> | IBM's official AI gateway/registry/proxy that sits in front of any MCP, A2A, or REST/gRPC API: unified endpoint, centralized discovery, guardrails, and plugin support: the... | Mcp, Python | Complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| Playwright MCP <small>★ 36,382 · 2026-08-23</small> | Playwright's official MCP server: structured browser control (navigate, click, fill, extract) via the accessibility tree rather than screenshots, so web tasks stay fast and... | Browser, Mcp, Typescript, Vision | Mostly simple | N/A / N/A | Open source |
| puppeteer-real-browser-mcp <small>★ 26 · 2026-08-23</small> | Puppeteer MCP with real-browser and anti-detection; for agents that need to drive sites that block headless. | Browser, Mcp, Typescript | Mostly simple | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| agents.md <small>★ 23,804 · 2026-08-23</small> | Open format for repo-scoped agent briefings; nested AGENTS.md files scope instructions per directory, so agents get a map of what exists and load only what's relevant. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Super simple | N/A / N/A | Open source |
| awesome-cursorrules <small>★ 40,646 · 2026-08-23</small> | Curated .cursorrules and skills that leverage Cursor's index-then-load model; the canonical collection for rules-as-progressive-disclosure in the IDE. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Super simple | N/A / N/A | Open source |
| context-mode <small>★ 20,102 · 2026-08-23</small> | Context-window optimization layer that sandboxes tool output before it reaches the model (claimed 98% reduction) and persists session memory across 17 agent platforms via MCP... | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | N/A / N/A | Restricted (elastic-2.0) |
| Headroom <small>★ 67,250 · 2026-08-23</small> | Compresses tool outputs, logs, files, and RAG chunks with content-aware compressors before they reach the model: claimed 20% fewer tokens for coding agents and 60-95% fewer for... | Mcp, Rag | Mostly simple | N/A / N/A | Open source |
| langgraph-bigtool <small>★ 556 · 2026-08-23</small> | Build LangGraph agents with large tool sets; retrieval and on-demand tool loading so agents scale beyond context without stuffing every schema upfront. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Slightly complex | Bounded / Durable | Open source |
| MCP-Zero <small>★ 511 · 2026-08-23</small> | Active tool discovery for autonomous agents: model requests tools by requirement; hierarchical semantic routing over 308 servers / 2,797 tools with ~98% token reduction (APIBank). | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / None | Open source |
| ToolGen <small>★ 184 · 2026-08-23</small> | ICLR 2025: unified tool retrieval and calling via generation; 47k+ tools without context stuffing: retrieval and invocation in one generative step. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| ToolRAG <small>★ 33 · 2026-08-23</small> | Semantic tool retrieval for LLMs; serves only the tools the user query demands (MCP-compatible), unlimited tool sets with zero context penalty. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Mostly simple | N/A / N/A | Open source |
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| AutoResearchClaw <small>★ 14,071 · 2026-08-23</small> | Fully autonomous, self-evolving research harness: multi-agent debate and citation verification carry a project from idea to a written paper without a human in the loop. | Multi-agent | Complex | N/A / N/A | <abbr title="Not established from the pinned sources">?</abbr> |
| DeerFlow <small>★ 80,648 · 2026-08-23</small> | ByteDance's long-horizon research harness: a LangGraph-based agent loop that researches, codes, and creates using sandboxes, memory, tools, and subagents behind a message... | Memory, Multi-agent, Python, Sandbox | Complex | Headless / Resumable | Open source |
| gpt-researcher <small>★ 29,099 · 2026-08-23</small> | Autonomous deep-research agent: web + local sources, citation-grounded reports, multi-agent and deep-research modes. | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Bounded / Retry | Open source |
| MiroThinker <small>★ 8,359 · 2026-08-23</small> | Deep-research harness tuned for long browsing-and-reasoning chains; benchmarked on BrowseComp, GAIA, and HLE by pairing a dedicated agent loop with its own MiroThinker models... | Evals | Slightly complex | Headless / Retry | <abbr title="Not established from the pinned sources">?</abbr> |
| openagents <small>★ 447 · 2026-08-23</small> | Platform for autonomous agents and autopilot-style workflows; decentralized/Nostr-oriented (Pylon runtime, actively shipped in 2026). | Build vs buy, Lifecycle hooks, Memory, Prompt optimization | Complex | Headless / Resumable | Open source |
Guide supplements (33)
These official products and researched candidates are absent from the pinned upstream snapshot. Their inclusion does not change the upstream 160-project count.
| Project | Role | Main capabilities | Adoption | Autonomy / Recovery | Licence |
|---|---|---|---|---|---|
| Agent Harness <small>★ 7 · 2026-08-28</small> | The README explicitly describes an adapter-driven control plane that delegates scheduling to the Codex runtime. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| AgentForge <small>★ 60 · 2026-08-28</small> | The README documents a ReAct-style loop that repeats model requests, typed tool calls, and observations until completion. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| agentic-harness <small>★ 84 · 2026-08-28</small> | The README documents a coding-agent loop that iterates through model tool calls against a workspace. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| AgentsMesh <small>★ 2,330 · 2026-08-28</small> | The README documents a control-plane and data-plane system for operating external coding agents. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| Amp | Amp presents its product as an agentic coding tool. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| Augment Code | Augment presents its product as an AI coding platform with agent capabilities. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| Autonomous Coding Harness <small>★ 7 · 2026-08-28</small> | The README claims a milestone-based autonomous coding loop with implementation, verification, and human checkpoints. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| Autonomous Workstream <small>★ 32 · 2026-08-28</small> | The README documents a plugin and CLI that sequences bounded tasks through an external coding-agent backend. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| Claude Code | Anthropic documents Claude Code as an agentic coding tool that reads codebases, edits files, and runs commands. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| Cursor Agent | Cursor presents Agent as its coding-agent product across editor and remote surfaces. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| DeepSeek Harness <small>★ 201,064 · 2026-08-28</small> | The official repository describes a developer-preview agent harness built on the Cordis plugin framework. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Mit |
| Devin | Cognition presents Devin as an AI software engineer. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| Devin Desktop | Devin Desktop, formerly Windsurf, combines an IDE with local and cloud coding agents. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| Factory Droid | Factory presents Droids as software-development agents. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| GitHub Copilot CLI | GitHub presents Copilot CLI as a coding agent for the terminal. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| Harness <small>★ 10 · 2026-08-28</small> | The README documents hardened container environments for agents rather than an agent decision loop. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| harness <small>★ 20 · 2026-08-28</small> | The README explicitly describes a unified subprocess wrapper for existing coding-agent CLIs. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| Harness CLI <small>★ 15 · 2026-08-28</small> | The README describes an orchestration and repair layer over Claude Agent SDK or Codex App Server runtimes. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| Hermes Autoresearch (Archived) <small>★ 8 · 2026-08-28</small> | The archived README says the experiment control loop moved into the hermes-loops monorepo. | Historical | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| Jules | Google presents Jules as an asynchronous coding agent. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| Junie | JetBrains presents Junie as its coding agent. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| Kimi Code CLI <small>★ 7,126 · 2026-08-28</small> | The official repository describes Kimi Code CLI as an agentic coding tool for terminals and IDEs. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Mit |
| Kiro | Kiro presents its product as an agentic development environment. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| Liza <small>★ 363 · 2026-08-28</small> | The source implements a control plane over external coding-agent CLIs, with a persistent YAML blackboard, isolated git worktrees, doer/reviewer roles, leases, recovery... | Adversarial-review, Crash-recovery, Multi-agent, Worktrees | Complex | Checkpoint gated / Durable | Apache-2.0 |
| Multica <small>★ 49,348 · 2026-09-09</small> | Human-agent work control plane that queues issue, chat, mention, and scheduled runs for external coding-agent CLIs through a daemon on a connected computer. | Issue-tracking, Local-daemon, Multi-agent, Worktrees | Complex | Bounded / Resumable | Restricted (multica license) |
| Open SWE <small>★ 10,624 · 2026-08-28</small> | The official repository describes Open SWE as an asynchronous coding agent for repository tasks. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Mit |
| OpenAgents <small>★ 4,005 · 2026-08-28</small> | The official repository describes OpenAgents as a network for persistent agents and shared workspaces. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Apache-2.0 |
| OpenCode Harness <small>★ 148 · 2026-08-28</small> | The README documents a coding-agent loop with tools, permissions, traces, evaluation, and repair feedback. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| OpenHarness <small>★ 12 · 2026-08-28</small> | The README documents a provider-to-tools agent loop and runtime injection points. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| Replit Agent | Replit presents Agent as a product that builds applications from user goals. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |
| Spettro <small>★ 33 · 2026-08-28</small> | The README documents autonomous goal runs, native tool calls, subagent workflows, and verification loops. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| Vigilante <small>★ 37 · 2026-08-28</small> | The README explicitly calls Vigilante a control plane over supported headless coding-agent CLIs. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> |
| Warp Agent | Warp Agent is a standalone terminal coding agent with interactive PTY support and optional cloud handoff. | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> | <abbr title="Not established from the pinned sources">?</abbr> / <abbr title="Not established from the pinned sources">?</abbr> | Proprietary |