Open Source Radar

Trending AI repositories

Tracked daily across the agentic ecosystem. Velocity is computed from our own snapshot history — collecting the first week of data now; repos are linked to the startups behind them.

1,381
Repos tracked
40
Linked to catalog
Jul 12
Last snapshot
TopicAllAgentsMCPLLMRAGCoding agentsInferenceVector DBsBrowser
SortTrendingMost starsNewest11 repos · page 1/1
lobehub/
lobehub

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

80k16kTypeScript
Mintplex-Labs/
anything-llm

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

In catalog: AnythingLLM
63k6.9kJavaScript
holaboss-ai/
holaOS

Your super agent for work: local-first, learn your working context in mins and never forget it.

5.5k392TypeScript
thClaws/
thClaws

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

1.2k158Rust
AI-Builder-Club/
skills

Codebase harness + loop engineer

843119Python
ruvnet/
metaharness

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

46351TypeScript
agentic-in/
inferoa

Inference-native Tokenmaxxing Agent Harness for Loop Engineering

44775TypeScript
Intelligent-Internet/
zenith

Zenith — a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.

24329Python
enmanuelmag/
agent-harness-kit

A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.

1718TypeScript
7-e1even/
learn-agent

学习Agent开发的笔记,尝试让Agent从可用到可靠

1138JavaScript
RightNow-AI/
AutoMegaKernel

An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch-1 LLM decode, paper: https://arxiv.org/abs/2606.09682

10210Python