Havuz

Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential con

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex

AI 应用开发、AI 编程实战与面试指南，涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。

Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.

wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new archi

Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.

Embedded agents your customers use to automate work, build views, and connect their tools.

<10 MB — self-hosted AI novel writer in a single Go binary with a web UI. Turn ideas into outlines and chapters with review, foreshadowing,

Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.

Give your AI agent a brain that remembers. Local memory system for Claude Code — 100% private, GPU-accelerated, zero cloud dependency.

CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.

Personal-Model First Self Evolving AI Agent 🐘

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, loca

An open-source Cotypist with macOS system wide AI autocomplete

A fast, native RSS reader — plus an agent-facing CLI so your AI agent can read, search and triage your feeds from the shell.

Inference-native Tokenmaxxing Agent Harness for Loop Engineering

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous

Plugin-first long-term memory for agent platforms — reference implementation of AMP (Agent Memory Protocol).

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence

T3Code, but in your terminal

What if your phone had no apps

Multi-LLM peer review for code decisions. Bring your own CLI; Chorus convenes 2-4 other LLMs to review the work before you ship.

Client for OpenClaw — Connect ClawWork to your own OpenClaw and unlock 10x multi-session productivity.

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

Official DESIGN.md files published by companies themselves. First-party design systems that AI agents read to generate consistent UI.

On-device meeting capture, dictation, and vault-native knowledge layer for macOS. Nothing leaves your Mac.

"CatchMe: Make Your AI Agents Truly Personal"

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Cal

Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory

Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/a

Open source AI company OS. 38 roles, 6 templates, 4-layer memory. Your AI company remembers everything — locally. npx clawcompany

帮你的 Claude Science 一键接入你自己的 API：DeepSeek / 通义千问 / 智谱 GLM / Kimi / MiniMax / 小米 MiMo / 硅基流动 / OpenRouter / 任意 OpenAI·Anthropic 兼容端点

Bounded project-memory skills for Codex CLI and Claude Code.

[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

IDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation into a unified desktop experie

Hojo-ASR is a high-performance speech recognition model powered by the LLM decoder.

AutoHarness: Automated Harness Engineering for AI Agents

Your First LLM-Wiki Conversation Knowledge Base

Harness-oriented agent system framework for production-grade LLM agent applications

AI-native, local-first video editor by Ribbi — runs entirely in the browser. Rust/WASM engine, WebGPU compositing, WebCodecs export; humans

Fixes prompt cache regression in Claude Code that causes up to 20x cost increase on resumed sessions

A custom Agent OS built to be hackable, heavily inspired by OpenClaw.

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

Local editor for importing, managing, running, and injecting APM-backed assistant packages.

Draw a store, generate LLM personas, and watch them shop — an isometric 3D sandbox for synthetic-consumer experiments.

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。