Havuz

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

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

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

Trustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.

A model-agnostic, stateless Go agent runtime featuring dual-IR planning, dependency-aware batch scheduling, capability-driven MCP/tool orche

一个基于 twikit 实现的 X (Twitter) MCP 服务端，轻量级工具。支持AI调用X平台功能，包含发推、回复评论、读取推文回复、私信收发、抓取用户主页详细信息、查看推文互动数据、推文搜索、点赞、转推、删推等多项工具。适用于 Claude Desktop、Cursor

Classify text in PHP without an LLM bill: typed decisions in 100+ languages, self-hosted. Laravel-ready SDK for Laya, a Jev AI alternative.

Rust-native, library-first coding-agent runtime and terminal CLI inspired by Pi, with composable LLM providers, tools, sessions, and plugin

Self-hosted AI-платформа с расширенными возможностями: RAG, агенты, веб-поиск, исследования, коннекторы, любые LLM и гибкие настройки

AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.

Claude Code ve Codex geçmişindeki tekrarlanan istekleri bulup proje içinde kullanılabilir kısa agent komutlarına dönüştüren bir Agent Skill.

Neden yükseliyor · Agent araçları arasında tekrar kullanılabilir iş akışlarına ilgi çekiyor olabilir; ancak yükselişin nedenini doğrulayacak bağımsız kanıt yok. 9 günlük yaşında 104 yıldız ve son 28 günde 17 commit başlangıç ilgisi ve hareketlilik gösteriyor; 2 farklı yazarla proje henüz küçük ölçekli.

qwen2API çok dilli (i18n) fork'u • Multi-language (i18n) fork of qwen2API — WebUI artık Çince, İngilizce ve Türkçe / UI now in Chinese, Engl

Governed neural weight editing and coding model adaptation. Native Rust patches, exact rollback, LoRA, Claude Code routing, and reproducible

A proactive personal AI. Works ahead. Lives on your computer.

Open Source Agentic Security Scanner

End-to-end AI-powered academic paper writing system — from idea generation and literature search to experiment execution, result backfill, a

iPhone, iPad and CarPlay client for the Hermes AI agent or any OpenAI-compatible model. Talk or type, watch it work, approve what it runs. N

Reverse engineered Deepseek chat into an OpenAI compatible API. Access V4 and R1 models through a simple REST interface without API keys or

Transformers for decision models: fine-tune, load and serve calibrated decsion-model on any Hugging Face model.

RAM efficient terminal agent harness for coding, cybersecurity, and automation.

Towards AI-Generated and Formally Verified Database Systems

Open source agentic SAST. The engine behind hundreds of disclosed zero-days. 100+ AI security agents, any repo or PR diff, bring your own mo

24 open-source agent skills that turn taste into instructions — ten genre identities, each proven by a same-brief before/after demo

Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context

Game development plugin for Hermes Agent: sound effects, music, NPC voices, pixel art, 3D models, Godot/Unity/Blender/Unreal, a playtester t

AI inference gateway and control plane for multi-provider routing, policies, caching, tools, and observability.

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

基于 ARTEX 的 AI 自主渗透测试系统，支持多 Agent 协作、资产探索与漏洞管理，提供本地部署面板。

A top for local LLMs: memory, paging, GPU and tokens/s for oMLX, Ollama, llama.cpp, vLLM and more

LLM serving engines that SkyDiscover builds on the fly for specific AI models and hardware: Qwen3.6-35B-A3B, Qwen3.8-Flash-Next and Flint on

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

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

Self-hosted private chat channel between you and your AI companion — PWA, Claude Code, or any LLM.

A native macOS assistant that reads the current screen and browser context when you need it.

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

Codex/Claude Code/Cursor的开源增强版，专注一句话实现复杂长程任务（教育、编程、办公、生活、娱乐、游戏）。部署在你自己的服务器上，团队用浏览器打开就能编程——包括手机。CLI & Web UI 双入口，Multi-Agent 协作，原生直连千问/DeepSe

梨园 Liyuan — 以 rp agent为主体的ai角色扮演应用

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimizati

Open-source platform for AI chat agents that answer from your own knowledge base. Hybrid RAG search in PostgreSQL, MCP and custom tools, gua

Fast, tiny AI coding agent for the terminal, written in Rust. One small native binary for Apple Silicon Macs. Works with OpenAI, Anthropic a

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall

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

MuseLite is an open-source AI workspace combining chat, Agent tools, browser automation, and scheduled tasks for users who enjoy Muse and Do

📊 电商数仓智能问数 AI Agent，最适合用于系统学习 LangGraph 的实战项目：基于 LangGraph、FastAPI、Qdrant、Elasticsearch、MySQL 与 React，完整实现元数据知识库、混合检索、自然语言生成 NL2SQL 生成校验、SQL

许愿特化器 · Wish Specializer — DSH 插件：让模型更出色地，不误解你的意思地，完成你的“愿望”。在短提示词+自带的Wish预设（PTC也可以）+重度的情况下，可以起到巨大的表现增益

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, les

Mine your Claude Code and Codex logs into a local you.md agent profile.

The agent harness you can fork. A working agent loop with compaction, sessions, approvals, a terminal REPL, a local dashboard and ACP, where

Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model,