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.

1,799

Repos tracked

Linked to catalog

Jul 20

Last snapshot

CategoriesAgents MCP Coding agents LLM RAG Inference Vector DBs Browser Workflows All →

SortTrending Most stars Newest1,799 repos · page 38/60

horang-labs/

tessera

Tessera — a workspace for organizing AI coding sessions across projects, collections, tabs, panes, and Git worktrees

26926TypeScript✓ Reviewed

tianma-if/

edgeever

Serverless, 100% free, and open-source Evernote alternative on Cloudflare with native MCP | 无需服务器、0费用、原生支持 AI Agent 的开源自托管『印象笔记』

26950TypeScript✓ Reviewed

modelstudioai/

cli

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

26818TypeScript✓ Reviewed

JamesShi96/

project-butler

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

26611Shell✓ Reviewed

wanghuan9/

skill-manager

SkillDock is a skill manager and MCP manager for installing, viewing, updating, and syncing AI skills and MCP servers, with Git-aware updates to track upstream changes and local modifications. SkillDock 是一个用于安装、查看、更新和同步 AI skills 与 MCP servers 的 skill 管理工具和 MCP 管理工具，并支持 Git-aware 更新，用于跟踪上游变更和本地修改。

2664✓ Reviewed

ryantsai/

KKTerm

Super-tool for vibe coders & system admins — terminals, SSH, SFTP, RDP/VNC, dashboards, install helpers, and a built-in AI assistant.

26339TypeScript✓ Reviewed

HarimxChoi/

google-surf-mcp

Google search MCP. One MCP replaces search + fetch + academic-paper extractor.

26332TypeScript✓ Reviewed

agent-sh/

computer-use-linux

Linux desktop control over MCP — AT-SPI, GNOME Shell, Wayland portals, ydotool

26331Rust✓ Reviewed

benmaster82/

Kwipu

Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.

26339Python✓ Reviewed

Moore-developers/

moore-wechat-article-downloader

本地优先的微信内容情报库：同步公众号文章，保存精选评论和互动数据，供 Codex/Claude Code 做内容研究。

26038Python✓ Reviewed

avifenesh/

bw24

From-scratch Rust+CUDA inference engine, bit-exact by construction — NVFP4, MoE, MTP speculative decoding, tuned against measured limits of one RTX 5090 Laptop (sm_120a).

26031Rust✓ Reviewed

kerlenton/

mcpsnoop

Wireshark for MCP. A transparent proxy that shows every real tool call between your AI client and your MCP servers, live in your terminal.

25317Go✓ Reviewed

smaramwbc/

statewave

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.

25211Python✓ Reviewed

Health-Yang/

MineEcho

Local-first Memory OS for personal AI assistants with L0-L3 memory, Wiki++ knowledge, skill routing, and TokenLess context compression.

25126TypeScript✓ Reviewed

ZeKaiNie/

universal-examprep-skill

Last-night exam-cram coach as a Claude Agent Skill: turns your slides, notes and past papers into a chaptered knowledge base + quiz bank, teaches only what's in your materials, and never fabricates (measured 100% out-of-scope abstention). Bilingual EN/中文 — the 期末极速备考 skill.

25013Python✓ Reviewed

wellingfeng/

UltraGameStudio

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

25028TypeScript✓ Reviewed

dongguatanglinux/

grok-build-auth

Protocol research client: x.ai signup → SSO → Grok Build OAuth → CLIProxyAPI auth export (authorized use only)

250116Python✓ Reviewed

scasella/

claude-dynamic-workflows-codex

Run Claude Code dynamic workflows on a local Codex (GPT) backend, plus an interactive run viewer

25017JavaScript✓ Reviewed

OmarH-creator/

Autonomous-Forge

This repo is automated and is fully AI-built and AI-maintained project that continuously plans, codes, tests, and improves itself.

2499Python✓ Reviewed

Eshaan-Nair/

ArcRift

Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.

24635TypeScript✓ Reviewed

nihe0909/

xiaohongshu-ai-workbench

《小红书运营手册 · AI工作台》: free Codex Skills for Xiaohongshu operations

24417Python✓ Reviewed

couragec/

LLMInternSkill

LLMInternSkill: LLM internship resume and job-search Codex Skill for resume polish, JD tailoring, evidence guard, interview grilling, and Project Scout. 大模型实习简历与求职工具箱。

24411Markdown✓ Reviewed

Lyra-stellAI/

BYO-LLM-WIKI

Build your own LLM-native WIKI (knowledge library). Search, extract, summarize, Q&A with contextual RAG, layered knowledge graph, and reinforced memory. Importantly use selected context to automatically generate skills, empowered by Claude subagents + CodeAct pipeline and gated by human review. Try Live Demo: https://byo-wiki-demo.onrender.com

2443Python✓ Reviewed

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.