AI Infra agents

Use ChatGPT with a private local memory

开源企业级 AI Agent 中台：模型接入 / 知识库 RAG / ReAct Agent / Skill 生态 / MCP / IM 机器人，一键私有部署

Compendio is an MCP server that indexes a project's markdown documentation and exposes it to any AI agent.

The Awen Engine — a local AGI memory organism that dreams. Recursive Harmonic Framework (RHF) reference stack: Gnostic Engine, Sovereign Client, Echo Protocol, Tesla Soul Engine.

大模型算法 / 应用 / Infra 岗位面试资料：10 份文档、345 道题、约 36 万字。含字节 11 篇面经实录、大模型八股上下篇、RAG / Agent / 推理部署 / AI Infra 四大专题，以及 12 家大厂面经横向对比。

Portable hybrid (BM25 + dense + RRF) retrieval engine and a label-free evaluation harness — extracted from a personal AI-assistant memory index and decoupled to run on any source tree.

SpringAI与LangChain4j学习dome

FAISS-based semantic search over any document type — LLM-calibrated section extraction, and pluggable embedding/chat providers (OpenAI-compatible or fully local).

RPG-OS is an open-source persistent LLM RPG system for solo role-playing with an AI game master. Build worlds and characters, keep campaign state in readable files, resume across chats, and use local or cloud models without locking your game to one provider. Built for long-running, open-ended text adventures and interactive fiction. For RPG gaming.

DSH PUA — 为 DeepSeek Harness 提供 PUA 任务推进、角色风味、验收循环和运行状态卡片 · PUA task persistence, personas, verification loops, and live status cards for DeepSeek Harness

A self-improving AI agent with a learning loop, multi-platform messaging gateway, and a paper-themed web dashboard.

Playing Pokemon Red using TypeSafe Jev

⚡ Ultra-fast O(1) Active Inference & Bayesian Cognitive Governor for AI Agents (Antigravity, Claude, Cursor) & Embedded Systems. Zero-alloc C11 core (<36KB) + FastMCP server.

Ask an AI assistant about your EPICS control system: live PV values, why a PV is disconnected, and where it appears across ChannelFinder, the Archiver and the alarm tree. Read-only by default.

Drive Blender headless from your AI agent: scaffold, build, animate from natural language. JSON in, JSON out.

Toolkit and libraries for running AI agents inside microVMs

Recursos de la charla Harness Engineering (Chihuahua Tech Week 2026): slides, demo en vivo, guia openclaw y checklist de 7 pasos.

Self-hosted AI automation platform with unified LLM gateway, agents, workflows, and messaging bots. OpenClaw alternative.

Mastra with built-in AI assistant

Accessibility runtime for streaming AI and agent interfaces—paced screen-reader announcements without rebuilding your UI.

Open source agentic programming environment for building, running, and inspecting AI workflows.

HERALD is an open-source CLI that emits the standard discovery files agents need to read your site and discover its agent-interaction capabilitie. One config object drives all of it. Each file is an independent open standard; pick the layers you want and HERALD generates only those.

Fast System-1 Decision, Arbitration & Safety Engine for Autonomous AI Agents (Powered by TypeSafe Jev)

An MCP server for discovering, ranking, and retrieving agent skills while minimizing context usage.

European memory system for AI agents with focus on compression and weighted information

Auto-generate Model Context Protocol servers from ABP Framework apps. In-process, permission-aware, multi-tenant.

JavaScript LLM agents on the XS engine, embedded in Swift. Snapshots, resident agents, confined tools.

Pure Jev that can "type" and drive towards task completion.

手搓 openclaw

Reasoning foundation for trustworthy agents.

Open-source Windows AI IDE built with .NET 8 WPF, featuring a fine-tuned local AI router (1.5B), live Blender & Unity copilots, self-healing agent loops, and multi-tool execution.

UCI course discovery platform with NLP via OpenAI. Discover any of the 6,140 courses UCI has to offer using natural language.

Open-source iOS client for LM Studio, chat with your local LLMs, fully offline and private.

Estimate GenAI prompt costs from a unified, auto-updated pricing table. This repo provides a tiny helper around OpenAI responses plus a parser for a curated model pricing table.

Extended Groq SDK with RAG (Retrieval-Augmented Generation), web browsing, and AI agent capabilities. Features include document retrieval, web search, URL parsing, and ReAct-style agents with tool use.

Multi-Agent AI with CrewAI | AI leveraging System 2 Thinking for intelligent decision-making. Scalable, adaptive, and efficient multi-agent collaboration for real-world applications.

RAG powered PDF Q&A with source citations. LangChain, FAISS and LLaMA 3.3 via Groq

This is the Rust language implementation of LangChain, The easiest way to write LLM-based programs in Rust

Standalone SDK workspace for building Aomi dynamic plugins.

PassiveQA is a novel question-answering framework that teaches language models when to answer, ask for clarification, or refuse to answer - instead of always attempting to generate responses.

UniMcp enables AI assistants like Cursor and Windsurf to interact with Unity

A connector for the MS Bot Framework (for offline/non-cloud-use)

Streamlit AI交互平台

Self-adaptive Planning Agent。自适应规划代理的多模态检索增强生成技术。

This repository contains a mental healthcare chatbot application

Domain-specialized Gemma 2 27B + Gemma 4 31B for SEC filings — fine-tuned on TPU v6e-8 with PyTorch/XLA FSDPv2, plus a Vertex AI Vector Search RAG demo (69 tickers × 381 filings). Same LoRA recipe, +3.5% / +5.8% BERTScore F1.

🦀 0xClaw official webpage (🏆 Hackathon Champion Project)

Biblioteca para criação e orquestração de agentes LLM com suporte à execução de funções, histórico persistente e integração com múltiplos modelos (Gemini, GPT, etc).

智能体Wynna，一个行业SOTA架构的通用人工智能助手。Agent Wynna, a general Artificial Intelligence assistant with an industry-leading SOTA (State-of-the-Art) architecture.

Personal AI agent with LLM-powered wiki knowledge base — drop documents in, agent auto-builds a structured wiki

A simple helm chart automating deployment of a retrieval augmented generation (RAG) solution on K8s Clusters.

Reference client for SpaceMolt - A TypeScript/Bun CLI for the AI MMO

The AI agent for the German Jordanian University, focused on accurate university documents retrieval

Modular AI runtime with LLM reasoning, memory, and pluggable action modules.

An agent framework for generating instragram-ready graphics for publications

Local, private AI for your laptop.

🧠 A warm, empathetic therapy-style mental health chatbot built with LangGraph, GPT-4o, MongoDB, and Streamlit — supports emotional understanding, risk detection, coping guidance, and memory-based chat context.

Modular framework for building topic-specific advisors powered by large language models, using LangChain, LangGraph, and Pydantic.

Discover and share powerful OpenClaw setups, skills, workflows, and guides.

Seelenmaschine是一个具有记忆和人格的LLM聊天机器人。它能够进行纯文本对话,并具有持久化的记忆系统,可以记住对话历史,并形成对用户的理解。Seelenmaschine is an LLM chatbot with memory and personality. It is capable of having plain text conversations and has a persistent memory system that remembers the history of conversations with the user and develops an understanding of the user.

jingu-trust-gate – deterministic admission layer that blocks LLM hallucinations from becoming system state

Agentic AI that tailors your resume and applies to jobs for you

Dental Caries AI Detection - detects caries using EfficientNetB3 model for advanced x-ray segmentation and classification.

One interface, every model at your command. Your local AI routing butler. | 一个接口，万模随心。你的本地 AI 智能路由管家。 | Built for OpenClaw & AI agents.

Python agent connecting local LLM and local SearxNG for web search

An experimental, local-first AI agent runtime built to explore safety-first tooling, RAG, identity models, and local persistence.

Governed context projection for AI work: receipts for what AI tools are allowed to see.

OpenCoordex is a production-grade Rust platform for enterprise multi-agent orchestration, combining multimodal input, ReAct reasoning, DAG/SOP automation, semantic cache, vector memory, and circuit-breaker governance.

Infrastructure for long-running AI agents. Track progress, decisions, and handoffs across sessions.

Autonomous AI Agent Infrastructure Platform — OpenAI-compatible AI gateway with MCP support, multi-agent orchestration, tool calling, observability, memory, RAG, AI workflows, and unified infrastructure for any LLM provider.

🚀 Dynamic node scaling for Clawdbot - parallel task execution with 6.8x average speedup

An Open-Source, Decentralized Marketplace for AI Agents. Enables A2A Collaboration, Discovery, and Interoperability for Multi-Agent Systems (MAS) and LLM Agents

Deeply integrated AI Agents powered by your OpenAI subscription and OpenRouter.

Give a complex task to a team of AI agents instead of just one. Multi-agent workflow orchestrator.

Intelligent Answers from Any Document

Persistent memory, context compression & profile visibility for 🦞OpenClaw🦞.

SamarthyaBot — A secure, multi-LLM powered AI agent with real OS, web, and automation capabilities for India.

SciMLAgents: Write the Solver, Not the Solution

A composable Python DSL for building GBNF grammars compatible with llama.cpp.

Track anything in streaming with Grounding DINO, SAM 2, and LLM

AI-Agent with RL capabilites in a Minecraft world

Task Manager MCP Server

A strict, deterministic LLM protocol for loading, reading and activating the DCQN.MATRIX Axiomatics from the OSF DOI (10.17605/OSF.IO/QWA6S), including anti-simulation safeguards and full formal reconstruction into DCQN_LOGIK_SESSION_V1.

Generate solution architecture diagrams

The ultimate native macOS AI Agent. Blends local MLX SLMs with 3D cognitive Metal rendering and autonomous system integrations.

Master Thesis Project about Agent and Multi-Agent Teaching Systems combined with Personal Memory

🗺️ MRRA: A Mobility Retrieve-and-Reflect Agent for Mobility Prediction.

Controllable and Transparent LLM Application Framework

🌳 Autonomous continuous learning framework for OpenClaw AI agents - Run 59 exploration rounds overnight

This package is a super handy JSON Schema Mapper for the LLM Agents project.

Runtime for agents operating on Canopy: wake on real work, route addressed coordination, and leave evidence.

ML/AI curriculum from first principles. Math, from-scratch implementations, papers, exercises, and interview prep across 60 files.

Infinite power but in a pendrive

RAG with Redis. Parallel implementations with/without guardrails.

AI-powered medical chatbot capable of providing symptom-based advice, recommending doctors, and retrieving medical documents.

Semantic Search on Langchain Github Issues with Weaviate