Havuz

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.

A self-hosted knowledge platform for humans and AI agents — publish wikis, blogs, and portable Agent Skills.

一套经过生产验证的 OpenClaw + Claude Code 实战知识库：涵盖生产部署、IM 接入、模型配置、安全加固，以及一系列可落地的 AI Agent 业务流项目（小红书发布 / 财务票据 / 智能早报 / CRM / 量化投研 / 密钥巡检自愈）。

Local-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health｜本地运行的 Rust TUI/CLI，审计 AI 编程 Agen

智能体 = 大模型 + Harness。深入剖析 Harness 工程原理、设计、实现与实践！

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, s

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interven

Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local proj

Local MCP server that lets AI assistants automate Origin/OriginPro for data and image processing.

MCP server that watches video footage and returns license-safe BGM matches, hook windows, and ffmpeg ducking specs for agents.

A ternary, zero-heap tiny language model that runs inside a $2 microcontroller — bit-exact Python <-> C99 <-> Cortex-M3 (QEMU) parity. Apach

Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi.

An extension of Karpathy's LLM Wiki pattern: atom layer, topic-branches, two-layer Lint. Distilled from running the pattern end-to-end.

Open-source multi-agent coding CLI for the terminal (TypeScript, MIT). Switch models mid-session; finish goals only when your test passes.

Claude Code skill: 5 AI agents analyze crypto, stocks, forex & commodities in parallel, adapt to your risk profile, and render an interactiv

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injectio

A Unified Memory Benchmark Suite for Memory-Augmented Agents

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one set

DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook

Open-source alternative to Claude Co-Work built by Claude. with BYOK

Search, archive, and recall your AI conversations. ChatGPT, Claude, Gemini, Grok, Kimi. Local-first, MIT licensed.

The full LibreChat experience, rebuilt natively for Android and iOS, and it works with whichever LibreChat version your server runs.

A lightweight annotation standard that helps AI agents navigate codebases faster, with fewer file reads and tool calls

Codex skill for analyzing still images and writing restrained, image-specific motion prompts.

A reference operating model for organizations where any role can be filled by a human or an agent, every process is built for agents first,

Custom output voices for ChatGPT, Codex, and Grok Bot — local and near real time.

Local-first agent workspace for knowledge, tasks, documents and verifiable workflows · Локальная агентная система для знаний, задач и провер

Speedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.

Local companion launcher and maintenance toolkit for the Codex desktop app.

HTTP bridge powering OpenClaw's AI agents via Claude Code CLI — manages persistent sessions, auto-resume, extended thinking, and provides a

No-No Debug — Self-evolution system for AI coding assistants. 10 minutes writing code, 2 hours debugging? This skill makes your AI remember

A simpler self-hosted alternative to Open WebUI. Bring your own API keys or local models. Native Android and iOS clients.

AI agents worth falling in love with. Built by the community, loved by everyone.❤️

AI中转站质量监控 · 模型验真 · Token成本优化 — RelayRadar 中转雷达

The open-source agentic framework to build, orchestrate, and operate production AI agents.

Open-source AI coding agent for your terminal — one Rust binary, 15+ LLM providers, 1,000+ models. A self-hostable Claude Code / Codex CLI a

English translation of MiroFish (github.com/666ghj/MiroFish) - A concise and universal swarm intelligence engine for predicting everything.

Local-first scientific literature RAG with frozen evidence, exact human annotations, paper screening with ASReview-style active-learning pri

Indian stock market MCP server for NSE & BSE — 48 tools (55 with aliases) for about 8,000 stocks: live quotes, financials, technicals, 326-r

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one r

A lightweight Windows framework for launching isolated AI desktop applications and CLI tools with independent profiles, workspaces, and envi

Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull r

The fastest way to put Volcengine Ark in your terminal and your AI agent — go from prompt to generated media, multimodal answer, or deploy

Blocks Network CLI and SDKs

CortexPrism — open-source AI agent operating system

Govern consequential AI agent actions in Docker with deterministic policy, human approval, and signed Decision Dossiers.

A self-hosted subtitle automation system with an LLM agent at its core — it identifies your media, judges whether each candidate belongs to

Start, stop, and duplicate dev projects with one click. The best workspace for running Claude Code, Codex, and other AI agents alongside you

🤖 Full-stack AI agent app built with React, TypeScript and LangGraph JS. Streaming, multimodal input, human-in-the-loop, native + MCP tools,

2026 年编程导航 AI 编程实战新项目，基于 Taro + React + FastAPI + DeepSeek 的 AI 闯关学习小程序，支持一句话 / 文本主题 AI 出题、闯关答题与即时讲解、联网搜索增强、RAG 私有知识库出题、AI 生图配图、微信登录与通关复盘报告。