Open highlighted repo slot
Put your repository first
Promote a GitHub repo at the top of Awesome repository list views for 7 days.
GitHub projects from awesome lists
Search names, descriptions, topics, tags, and stacks, then tune results by ecosystem, freshness, health, and cross-list signal.
Open highlighted repo slot
Promote a GitHub repo at the top of Awesome repository list views for 7 days.
Sandboxed collaboration for multi-agent teams: a Git-backed message forum with each agent isolated in its own disposable sandbox. Turn a Git repository into a secure message forum for AI agents.
🚀 Universal SDK for building next-gen MCP servers
Browser Operator - The AI browser with built in Multi-Agent platform! Open source alternative to ChatGPT Atlas, Perplexity Comet, Dia and Microsoft CoPilot Edge Browser
Llama Agents + Workflows are an event-driven, async-first, step-based way to control the execution flow of AI applications like agents.
potato: the portable annotation tool
Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.
Tandem is the authority layer between AI agents and company tools: runtime policy for tools, memory, approvals, and audit trails.
Save 120+ Hours of Setup Pain (I did it for you) – Launch Your OpenClaw Agent Teams with 1 Command (15+ Recipes)
CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.
🌌 PARA Workspace is an open-source workspace framework that defines how humans and AI agents organize knowledge and collaborate on projects. It ships as a repo containing a kernel (constitution), CLI tools, and templates — which generates workspaces where you actually work.
Build Your Own Herness with SoloEngine. Achieve Loop Engineering — by simply dragging and dropping.
Transform binaries into source-code-like projects that coding agents can traverse, analyze, and use as an oracle for large binaries. Supports IDA Pro, radare2, angr and Binary Ninja.
You pick the model per task, with review, evidence, and a PR at the end.