🌐 English · Português
Curated index of agent harnesses — frameworks, coding CLIs, memory layers, orchestration platforms and enterprise systems — used as study and benchmark references.
Coding · Multi-agent · Memory · Assistants · Spec-driven · Self-improvement · Workflow · Protocol · Eval · Enterprise · Skills
by Alan Nicolas
33 projects. 11 categories. Opinionated curation. Contains no original code — all repos are forks/clones for analysis. See Local mirror to reproduce the bench.
- 💻 Coding agents & CLIs — IDE-native, Terminal/CLI, Templates
- 🤝 Multi-agent orchestration
- 🧠 Memory & knowledge
- 🦾 Personal assistants
- 📐 Spec-driven & methodology
- 🧬 Self-improvement loops
- ⚙️ Workflow & durable execution
- 🔌 Protocol & infrastructure
- 📊 Evaluation & observability
- 🏢 Enterprise platforms
- 🧩 Cross-agent skills
- 🗒️ Patterns observed
- 🛠 Local mirror
- 🤝 Contributing
- 📄 License
| Project | Stack | Differential |
|---|---|---|
| anthropics/claude-code | TS + Ink + Bun | Snapshot (~512K LOC) of Anthropic's official CLI; canonical reference for terminal-UI coding agents. |
| openai/codex | TS + Rust | OpenAI's official CLI coding agent with IDE integrations and a focus on local automation. |
| Aider-AI/aider | Python | Most-used pair-programming CLI in open source; git-native with auto-commits per iteration. |
| All-Hands-AI/OpenHands | Python | Most-starred autonomous agent on GitHub (formerly OpenDevin); standard SWE-bench benchmark. |
| Project | Stack | Differential |
|---|---|---|
| open-gsd/gsd-pi | TS (Pi SDK) | Living GSD: auto-milestones, worktree isolation, .gsd/ memory, Agent Skills runtime. (gsd-2 is the archived snapshot.) |
| garrytan/gstack | TS + Playwright | Personal software factory by YC's president; 24 specialized agents in a multi-role workflow. |
| obra/superpowers | TS (Claude Code plugin) | Pure red/green TDD with parallel subagents; reports a 94% PR rejection rate. |
| Project | Stack | Differential |
|---|---|---|
| JCodesMore/ai-website-cloner-template | Next.js + shadcn | Pixel-perfect site cloning via parallel builder agents in the /clone-website command. |
| Project | Stack | Differential |
|---|---|---|
| bmad-code-org/BMAD-METHOD | TS | 12+ personas (PM, architect, UX…) with "Party Mode" running multiple in one session; agile applied to agents. |
| crewAI-inc/crewAI | Python | Framework for collaborative role-playing agents with shared goals. |
| microsoft/autogen | Python | Microsoft's multi-agent conversational framework; research baseline for message-based coordination. |
| paperclipai/paperclip | TS + React + Postgres | Manages agents like employees — org charts, budgets and goals. |
| grandamenium/claude-remote-manager | Bash + TS | Claude Code 24/7 controlled via Telegram; persistent cron survives restart. |
| Project | Stack | Differential |
|---|---|---|
| mem0ai/mem0 | Python | Leading memory layer in 2025; native vector store and a simple API for LLM apps. |
| milla-jovovich/mempalace | Python + Chroma | 96.6% R@5 with verbatim storage (no paraphrasing); local-first, no API keys. |
| garrytan/gbrain | TS + PGLite + pgvector | 95.32% LongMemEval recall_all@5 with Voyage rerank (hybrid-only 93.19%; expansion@k=5 is 54.89%); entity self-wiring without an LLM. |
| MemoriLabs/Memori | Python | LLM-agnostic, agent-native memory infrastructure; 81.95% on LoCoMo, SQL-backed. |
| Project | Stack | Differential |
|---|---|---|
| openclaw/openclaw | TS + SwiftUI + Kotlin | 20+ channels (WhatsApp, Telegram, iMessage…) running on-device. |
| NousResearch/hermes-agent | Python asyncio | Auto-creates skills; runs on a $5 VPS or serverless with hibernation; multi-model. |
| danielmiessler/LifeOS | Skills + hooks | Personal life OS: TELOS/ISA as living spec, Pulse dashboard, receipts-gated releases (claim ≠ done). |
| Project | Stack | Differential |
|---|---|---|
| github/spec-kit | Python + TS | Executable specs that generate implementation; GitHub's official methodology. |
| gsd-build/get-shit-done | TS | Solves "context rot" via spec discipline and meta-prompting; in use at Amazon, Google and Shopify. |
Systems that iterate, mutate and optimize against a metric — descendants of karpathy/autoresearch and the "AI scientist" lineage. See also alvinreal/awesome-autoresearch for the full index.
| Project | Stack | Differential |
|---|---|---|
| ShengranHu/ADAS | Python | Automated Design of Agentic Systems (ICLR 2025); meta-agents that invent novel agent architectures by programming them in code. |
| SakanaAI/AI-Scientist-v2 | Python | Workshop-level autonomous scientific discovery via agentic tree search; removes v1's template dependency and generalizes across domains. |
| gepa-ai/gepa | Python | GEPA (Genetic-Pareto) — ICLR 2026 Oral; reflective prompt evolution that outperforms RL (GRPO); optimizes any textual parameter against any metric via natural-language reflection. |
| Project | Stack | Differential |
|---|---|---|
| vercel/workflow | TS + Next.js + PG | Deterministic replay via event log; split VM + step runtime. |
| github/gh-aw | Go + Markdown | Agentic workflows written in natural language, executed sandboxed inside GitHub Actions. |
| Project | Stack | Differential |
|---|---|---|
| modelcontextprotocol/servers | TS + Python | Official Model Context Protocol repo; 50+ reference servers. |
| Project | Stack | Differential |
|---|---|---|
| langfuse/langfuse | TS + Next.js | Most popular open-source observability for LLM apps; tracing, eval and prompt management. |
| Project | Stack | Differential |
|---|---|---|
| dataelement/Clawith | TS | "OpenClaw for teams": digital employees with soul.md + memory.md, org chart and multi-tenant delegation. |
| microsoft/agent-governance-toolkit | Multi-lang | Sub-ms policy enforcement covering 10/10 of the OWASP Agentic Top 10; runtime security. |
| langgenius/dify | Python + TS | Most popular low-code platform (129k+ stars); ready for teams and production. |
| Project | Stack | Differential |
|---|---|---|
| alchaincyf/huashu-design | Skill (multi-agent) | Agent-agnostic skill (Claude Code, Cursor, Codex, OpenClaw, Hermes) that delivers ready-to-ship design — animations, clickable prototypes, slide decks, infographics — from a single prompt. |
Cross-cutting axis, grouping harnesses by recurring technique/architecture:
| Pattern | Projects | Note |
|---|---|---|
| First-class memory | gbrain, mempalace, gsd-pi, hermes-agent, mem0, memori-labs, LifeOS | Memory as a separate, measurable component — not a bolt-on. |
| Spec-driven | spec-kit, get-shit-done, superpowers | Pragmatic alternative to "vibe coding"; specs drive execution. |
| Multi-persona / party-mode | BMAD-METHOD, crewAI, autogen, paperclip, gstack | Coordination across multiple roles inside a single harness. |
| Parallel subagents | superpowers, ai-website-cloner-template, gstack | Task fan-out to specialized agents. |
| Durable / replay | vercel/workflow, gh-aw | Event-sourced; survives crashes; reproducible. |
| Local-first | mempalace, openclaw, gbrain, hermes-agent, LifeOS | No cloud dependency; on-device or self-hosted. |
| Governance / policy | agent-governance-toolkit, Clawith | Runtime security and agent org charts. |
| 24/7 persistent | claude-remote-manager, hermes-agent, gsd-pi | Cron, hibernation, automatic resume. |
| Self-improvement / autoresearch | ADAS, AI-Scientist-v2, gepa, superpowers | A loop that measures, mutates and optimizes — code, prompts or architecture. |
To clone/update every project in parallel:
./update.shThe script reads repos.tsv, clones whatever is missing and runs pull --ff-only on the rest. Lines starting with # are skipped (the next-level-outreach remote has been 404 since 2026-08-23; the local clone is kept).
Legend: [+] cloned · [↑] updated · [=] up-to-date · [x] error
Latest sync notes: _bench/_research/os-update-convergence-2026-09-05.md.
PRs welcome. To add a harness:
- Add an entry to
repos.tsvin the formname<TAB>url<TAB>branch. - Add the row to the matching section's table in the README:
[owner/repo](url) | Stack | One-sentence description with the technical differential. - If it represents a new recurring pattern, add it under 🗒️ Patterns observed.
Inclusion criterion: the project must be a harness — something that orchestrates, executes, or gives memory/tools to an LLM. Pure model libraries (no agent loop) and generic infrastructure (raw vector DBs, etc.) are out of scope.
This list is released under CC0-1.0.