Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
kiso
Agents & frameworksThe durable runtime for AI agents: event-sourced sessions, approvals that persist across processes, exact resume after a crash. A 2,200-line TypeScript kernel, and kiso-code, the coding agent built on it.
git clone https://github.com/vincemakes/kiso.git -
cuga-agent
Agents & frameworksCUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.
git clone https://github.com/cuga-project/cuga-agent.git -
wmux
MCP serversThe ADE for AI agents. Automate everything else. Do your true work.
git clone https://github.com/openwong2kim/wmux.git -
Arcgentic
MCP serversMechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.
git clone https://github.com/Arch1eSUN/Arcgentic.git -
awesome-jev
SkillsJev demos, projects, SDKs and skills, with source links and a curated X gallery.
git clone https://github.com/Amal-David/awesome-jev.git -
heym
MCP serversBuild agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.
git clone https://github.com/heymrun/heym.git -
browser-debugger-cli
SkillsLet Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP needed.
git clone https://github.com/szymdzum/browser-debugger-cli.git -
awesome-multi-agent-orchestrators
Agents & frameworksAwesome-style curated list and directory for multi-agent orchestration.
git clone https://github.com/Agent-Analytics/awesome-multi-agent-orchestrators.git -
pydantic-deepagents
Agents & frameworksOpen-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.
git clone https://github.com/vstorm-co/pydantic-deepagents.git -
UltraData-SFT-Agent-2609
Datasets & benchmarksHugging Face dataset by openbmb
openbmb/UltraData-SFT-Agent-2609 -
Martin Loop
MCP serversOne system around coding agents to run, verify, recover, and hand off software work.
@martinloop/mcp@0.9.0 -
hippo-memory
MCP serversStop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). Local-first. Measured: about half the repeat mistakes of built-in memory alone, at the same cost.
git clone https://github.com/kitfunso/hippo-memory.git -
kanzo
MCP serversSelf-hosted, sharable kanban for humans and agents. One 4.7 MB binary, 5 MB of RAM, 10 to 60 tokens per agent reply, starts in 3 ms, zero setup.
git clone https://github.com/emanuele-em/kanzo.git -
self-bench
Datasets & benchmarksBenchmark coding agents and models on your own repository with private Harbor-formatted evals built from its merged pull requests.
git clone https://github.com/mupt-ai/self-bench.git -
mi
Tools & appsself-extending sandboxed agentic harness. a loop, two tools and an llm
git clone https://github.com/av/mi.git -
paneflow
MCP serversNative terminal multiplexer for coding agents. Persistent sessions, Git worktrees, diffs, and an integrated editor. Built with Rust and GPUI.
git clone https://github.com/arthjean/paneflow.git -
lazyskills
Tools & appsmission control for agent skills
git clone https://github.com/alvinunreal/lazyskills.git -
Hill-Climb
SkillsMake your coding agent prove "done". Each change is kept only if a locked test or benchmark scores it better. Claude Code and Codex skill.
git clone https://github.com/Bil0000/Hill-Climb.git -
paperthin
SkillsThe skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.
git clone https://github.com/LilMGenius/paperthin.git -
troupe
Agents & frameworksRun a team of coding agents you can actually watch: one approved plan, each role in its own tmux window and git worktree, on Claude Code or Codex.
git clone https://github.com/hitianqi/troupe.git -
agy-staff
Agents & frameworksHire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code, OpenAI Codex, and DeepSeek Harness.
git clone https://github.com/keli-wen/agy-staff.git -
skills
SkillsAgent skills and MCP servers that teach coding agents to write, run, and repair Momentic tests.
git clone https://github.com/momentic-ai/skills.git -
Linghun
Tools & appsAGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.
git clone https://github.com/linghungegeg/Linghun.git -
friday
Agents & frameworksA local-first desktop alternative to Grok Bot, OpenBot, T3 Code, Herdr and Orca. Run Claude Code, Codex, Cursor and 13 more coding agents as one team on your own computer: a shared board, agents that check each other’s work, and no account. Free. macOS, Windows, Linux.
git clone https://github.com/splashxmoon/friday.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.