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.
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。
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.
Web UI for Pi Coding Agent that keeps sessions alive in real workspaces.
Codex skill for auditing and tuning Codex Desktop context/tool surfaces
Embedding-based code duplication detector
Control your local Codex sessions remotely through Discord on your phone or browser.
Antidote for fluffy specs, a toolkit for fact-driven development with AI agents
Drive the OpenAI Codex CLI as a background implementer, brief it, review its diff, land the commit yourself.
IJFW — It Just F*cking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow.
The work experience layer for autonomous agents. Open-source core: https://github.com/ShuxinYang111/oysterworkflow-core
A macOS Dynamic Island for AI coding agents: Claude Code, Codex, Gemini CLI, Cursor, hooks, skills, and local agent management.
中文优先的 Vibe Coding / AI coding engineering workflow guide: specs, agents, worktrees, skills, CI, and review.
One folder. Every session knows where you left off. — An open-source methodology for AI-assisted projects.
One file. Under 200 lines. Zero dependencies. It's a coding agent.
Git-native memory for coding agents. Repo memory before the diff.
Local-first memory layer for AI coding agents. Captures issues, attempts, decisions, and cross-project library gotchas — your AI starts experienced, not amnesiac. Native MCP server verified across Claude Desktop, Cursor, Antigravity, and Codex. 100% local · no cloud · no telemetry · MIT.
Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).
Carbon Code 是一款类似 Claude Code 的代码开发工具，也是中国第一个基于 DeepSeek 的代码开发工具，Token 成本节省 90% 以上。它可以实现自动任务拆分、自动开发、MCP 测试，以及与 Claude、Codex 等多 Agent 协作，能力接近 Claude Sonnet 4.6
Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent handoffs (−53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.
The self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
Top Free AI Developer Tools for 2026
Best AI Coding Workflow Plugin Pipeline 2026
HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code
Claude Code AI Pipeline 2026 – PEV Framework Harness Plugin for Developers
Top Open-Source AI Engineering Platform 2026 Qyvaria Kernel
Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.
Uncensored AI coding agent in your terminal. Does the work, skips the sermon. 256K context, crypto-only billing, no card on file.
Durable MCP control plane for long-running Codex Desktop tasks
Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in Claude Code, Codex, Cursor, Aider, OpenHands.
The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.