GitHub agents

Beast Agent is a TUI to an agent, much like Pi or Claude Code. But compiled. Containerized. Multi-model. Agentic. Perfect for long-horizon tasks.

High-performance local SQLite FTS5-based tool output cache and MCP multiplexer for AI agents.

Portable workflow protocol for safer multi-agent AI coding with explicit review, evidence, handoff, and git gates.

Fusion — a Claude Code skill: convene a panel of frontier models (Opus 4.8 + GPT-5.5 xhigh), judged into one grounded answer. Deep Thought, with receipts.

Session resources and patterns for orchestrating multi-agent workflows in VS Code — decomposing work, forking vs. delegating, and verifying quality at scale. From Microsoft Build 2026.

The open schema for multi-agent workflows — define agents, roles, models, skills, tools, access policies, and handoffs in a single versioned document.

Production-grade skills, custom MCP servers, and real projects built with Grok Build 0.1 (grok-build-0.1). The definitive toolkit + living showcase for xAI's agentic coding model. Sole author & maintainer: Cobus Greyling

A visual workspace for designing, configuring, and managing OpenCode agent teams.

Portable Goal-Based SDLC for Claude Code — interactive goal-mode + autonomous park-and-continue loop-mode, installable into any repo as a plugin. Zero runtime deps.

AI-Agent with RL capabilites in a Minecraft world

Knowledge vaLidated Expert AI assistant for neuroscience

A collection of LangChain / LangGraph/DeepAgents examples from the official documentation

Local-first RAG platform for technical document libraries. Features FastAPI, ChromaDB, and active retrieval (FLARE) powered by Ollama.

The open framework for governed AI development: EU AI Act compliance, PII redaction, MCP proxy, prompt-injection firewall. Python + Rust, Apache 2.0

A reproducible benchmark for studying when prompt optimization improves multi-agent LLM systems.

Learn from any GitHub repo systematically with AI agents guiding you through architecture, flow, patterns & takeaways

Multi-agent coordination + harness adapters + portable CLI utilities for Claude Code / Cursor / Codex.

AI research agents + scientific image viewer for bioimaging & neuroimaging — LangGraph agents, GPU inference, and native in-browser OME-Zarr / TIFF / NIfTI / HDF5 viewers.

An embodied agent framework for orchestrating long-horizon, multi-module tasks in real-world robotics.

A local AI-powered OS assistant for Windows that organizes files, monitors system pressure, suggests cleanup actions, and stays privacy-friendly by running with local tooling such as Ollama.

Let any MCP agent build, run, and debug FiveM resources live.

The modern, local-first PostgreSQL client with a natural-language SQL assistant.

Your agent wastes context. Distill fixes it.

Agent & worker factory (in construction) — self-hostable hub; tools plug in over NATS, CLI, skills, API

Benchmark LLMs on your own codebase. Repo-specific probes, blind rubric-based judging, and correctness-first rankings.

AI study app that decides what to study — persistent tutor memory, grade tracking with a 'what do I need on the final' calculator, and study through your own Claude via MCP. BYOK on Next.js + Supabase.

Claude中转站推荐，国内直连可试用稳定可靠的Claude API中转站

Claude Code skill that invisibly rates every external resource (WebFetch / WebSearch / MCP / curl) via PostToolUse hooks. Two rater backends: Anthropic API key or claude.ai subscription via 'claude -p'.

Persistent AI governance for Claude Code — three-tier council deliberation, P10 pre-execution plans, and deterministic confidence scoring grounded in your own past decisions.

Run Anthropic's Claude Code as a multi-surface A2A custom agent inside Gemini Enterprise App. One conversation across mobile, web chat, and Cloud Workstation terminal.

A full AI coding environment: Jean Claude Van Docker 💪

Command Autopilot — use 100% of Claude Code while memorizing zero commands. Silent automation, right-moment suggestions with benefits, self-evolving to your habits.

Turn any raw prompt into a production-ready, XML-structured prompt optimized for Claude Opus 4.8 - 11 rules, complexity-based routing, hard prompt: trigger.

Wisdom before intelligence. A provenance-aware reasoning layer that abstains instead of fabricating — stops LLMs inventing attributions and merging distinct traditions. Measured: 0% fabrication on unknown-answer traps (vs 17–25% raw); −12.5pt hallucinated attributions at 0% false-positive cost. An AGI-candidate proof package, not proven AGI.

Halo AI 智能套件：RAG 智能问答、AI 搜索、脑图、摘要、写作辅助、意图路由、评测与运营智能体

Immersive 3D Tamil tea kadai portfolio — Three.js procedural WebGL, zero 3D models. ML Researcher · Systems Builder · Cloud (AWS/GCP) · Vigneshwar L

Agent-first GraphRAG workflow that turns local documents into reusable knowledge graphs. Drop files in, let skills extract entities and relationships, then query a persistent graph artifact locally—no cloud or pipeline setup required also the graph can be exported to neo4j and qdrant for deployment

[EMNLP 2025] M-LongDoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework

Free AI Engineering curriculum for Afghan students — powered by Ollama, 100% offline, zero cost

Hosted MCP server + slim wiki projection of the First Principles Framework (FPF) by Anatoly Levenchuk. Bounded, vectorless retrieval over 292 patterns and 3 curated routes — addressable by stable FPF IDs, synced daily from ailev/FPF.

Maximum Claude output with minimum tokens. 50+ compression patterns, 10 system prompts, benchmarked results. Star to unlock usage.

抄袭者 Skill - 把开源项目抄过来变成你自己的 | 兼容 Claude Code / Codex / OpenClaw / Hermes Agent | AI Agent Skill that clones, rebrands, and customizes open source projects

AI 编程代理框架，支持多模型接入，并通过技能化系统统一编码与自动化工作流。

"Let ElBot Feel Everything." ElBot is a lightweight Agent/Chatbot framework written in Go, it's token-efficient, easy to manage, and capable of perceiving the world.

Self-learning AI agent framework with 6-layer memory evolution engine. Build intelligent agents for any business scenario.

🔥 A local-first AI agent mainframe built in Rust with capability-based security and event-stream architecture... 💎 Preloaded with a trusty assistant Leon the chameleon, a fully customizable to user needs featuring quantum encrypted internal blockchain security... 🦎

AI-powered course assistant that helps students study from class materials with grounded guidance, review support, and exam preparation.

Hermes AI agent market-analysis skills (crypto / saham IDN / forex+commodity). Pluggable per-asset analyzers used by the Hermes agent.

Open-source AI agent framework for autonomous Memecoin trading, LLM orchestration, and blockchain intelligence.

📄 Transform your PDF documents into actionable insights with this RAG-based Question-Answering App for efficient and accurate responses.

A modern, multi-agent desktop AI client built with Tauri, SvelteKit, and Rust.

Iterative optimization for AI agents. Turn models into accurate, structured, production-ready systems.

A fully autonomous AI agent that runs on a ESP32 microcontroller (S3 and P4) — tool use, persistent memory, cron scheduling, multi-channel messaging, all on-device with modern web UI. Cloud-backed persistence (S3-compatible) protects your data from flash wear and reflashes via transparent write-through replication. Works with any LLM provider.

Semantic, persistent knowledge graph memory for LLM-based and multi-agent systems, exposed via the Model Context Protocol (MCP).

A Text2SQL system built using Langgraph Agents.

Build a conversational chatbot that can remember context and retrieve external information during conversations.

FastAPI RAG microservice powering the AI layer of EduMate, indexes 50+ CS textbooks into ChromaDB for Dev and Qdrant Cloud for development, retrieves via cosine similarity, and generates grounded answers through Groq Llama 3.3-70B. Custom retrieval optimizer handles deduplication and hybrid reranking.

AI CFO Agent: Self-hosted financial intelligence. 24 features, $0.003/run. FastAPI + LangGraph + Next.js + Claude Haiku. Upload CSV → get KPIs, fraud detection, runway analysis.

Cross-examination protocol for multi-LLM CLI sessions — blind claims, command-verified debate, git-diffable bus. Zero-dep single-file Python.

DesireCore Agent OS. An open, delegation-based AgentOS (Agent Operating System) — a teachable, file-based AI companion desktop app you can grow.

Postgres + pgvector memory provider plugin for hermes-agent. Multi-agent storage layer with per-minion themes, async writer, no LLM in the memory hot path.

Multi-model AI research pipeline based on Stanford's STORM methodology. Research any topic with 4 parallel AI models via OpenRouter Fusion -- near-frontier quality at near-zero cost.

AI-powered interactive animated story generator — script, SVG art, and animations generated by Claude agents on AWS

Open-source Poster Generation from Any Input Source Across Modalities and Domains

AEP is an open observability protocol for AI agent systems - giving you structured event capture, real-time session tracing, and multi-agent workflow visibility in a single self-hosted deployment.

Orchestrate a fleet of real Claude Code agents on your Claude subscription, not per-token API bills - local-first.

The agentic runtime to build production-grade AI agents at scale.

A minimal, production-shaped ReAct agent framework built from scratch in pure Python think-act loop, typed tools, layered memory, guardrails, and an eval harness. No LangChain.

The open, model-agnostic platform to build your own AI agent and run it everywhere — self-hosted, safe by default.

Composition root for production agent services — fork, customize, ship. Built on the foundry-agent-* packages.

Embedded memory for TypeScript agents.

Official repository for SPROUT - ICML 2026

Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation

ServiceNow Coding Standards for Humans and AI Agents.

Local-Ai Agent with custom integrated tools & skills. Ultra-light. Hyprland, Omarchy, Odysseus, and Hermes.

MCP server for Pharo

Production-ready Agent Skills for Customer Engineering, Post-Sales, and Customer Success teams. Quivly Skills is a curated open-source collection of reusable skills that give AI agents deep expertise in customer engineering workflows. Every skill follows the official Agent Skills specification.

Dr-CiK: A Testbed for Foresight-driven Agents

Turn messy artifacts into a cited knowledge graph and a queryable RAG packet, with baidu/Unlimited-OCR visual intake.

A local, provider-neutral runtime for governed software agent loops.

🛡️ Automated security scanner for MCP (Model Context Protocol) servers — 58 rules for prompt injection, credential exposure, SSRF, tool poisoning & source-level credential-handling flaws. pip install mcp-safeguard

Production ready LangGraph multi-agent orchestration template with supervisor routing, FastAPI + Streamlit chat UI, MCP tool calling, local RAG + knowledge graph retrieval, PostgreSQL memory, per-user auth, and CI/CD.

Agent Skills for Steam wishlist filtering and evidence-based game purchase recommendations.

Reusable Go base agent on the Google ADK — multi-provider (Gemini, Vertex, Claude on Anthropic + Vertex), MCP-native, with AGENTS.md, skills, and permissions wired up.

Daily tracker for frontier AI lab papers, model cards, system cards, and technical reports

Build real websites using natural language - no coding required

An autonomous orchestration harness for Claude Code: brief it like a teammate, it conducts Claude Code in your seat. Git stays locked.

Documented lead-gen, CTA, social proof, urgency, and interactive tooling patterns. Research-backed pattern catalog companion to rampstackco/claude-skills.

⚡Switch LLM Providers for Any App with One Click: A Single-Binary LLM Gateway with Auto API Translation and Traffic Inspection.

Autonomous engineering pipeline for Claude Code — /drive runs the task lifecycle (plan → implement → review → harden → finalize → ship) with two human gates, gstack planning, and codex cross-model review.

反封号.skill — Claude Code / Anthropic / OpenAI account suspension risk detection, IP cleanliness scoring, compliance preflight, and appeal-packet skill. Compliance-only; no ban evasion.

Track your Claude.ai session, weekly, and Claude Design usage in real time. Manifest V3 extension for Chrome and Firefox.

Scriptable wrapper around the Claude Code TUI — flat-rate subscription, not metered Agent SDK credits

Audit sales offers (landing pages, pricing tiers, lead magnets) using Alex Hormozi's frameworks from $100M Offers and $100M Leads. Returns a scored audit with prioritized fixes. MIT licensed. By @johnericforte.

macOS /manpages skill for AI agents. 15,299 macOS commands = 0 hallucinated terminals

Open-source DeepWiki alternative: AI-generated documentation and natural language Q&A for any Git repository.

VibeCoded Tools - Orchestrator: improve your Claude Code!

Local-first semantic search for your ChatGPT, Claude, and AI conversation history. Python CLI + MCP server for Claude Desktop. Uses sentence-transformers + ChromaDB. No API keys, nothing leaves your machine. Part of the Resonant ecosystem.

Embedded memory engine for AI agents and local-first apps — NodeDB in-process, offline-first, syncs to the cloud.

Single-process database for AI apps: vector, graph, lexical, and hybrid search with durable jobs in one binary.