Hugging Face rigs 52
Agent setups committed in repos that use Hugging Face. Median context tax 2.9k tok (index: 2.3k), average guardrails 0.4/5. Filter and sort these in the directory →
Top MCP servers
python 2/path/to/hallucination-firewall 2${claude_plugin_root:-.} 1paper-preflight[mcp] 1mcp.arif-fazil.com 1llmslim[mcp] 1lcc.lookadev.com 1recall-codex-mcp 1
bojieli/ai-agent-book
《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码
Skill Collector 1.3k tok · · Q0
topoteretes/cognee
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
Skill Collector 22.0k tok · · Q20
semantica-agi/semantica
Graph-Native Infrastructure for Context and Accountable AI Systems
Skill Collector 1.1k tok · · Q0
raullenchai/Rapid-MLX
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server and Mac app for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Release-gated with Claude Code, Codex CLI, Aider
Pragmatist 4.9k tok · · Q3
heshengtao/super-agent-party
⭐ All-in-one AI companion! Super Agent Party = Self hosted neuro sama + openclaw! ⭐ 全能AI伴侣!超级智能体派对 = 自托管neuro sama + openclaw!
Minimalist 1.6k tok · · Q0
kayba-ai/agentic-context-engine
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
Pragmatist 1.6k tok · · Q15
youssofal/MTPLX
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenA
Minimalist tok n/a · · Q15
Memento-Teams/Memento-Skills
Memento-Skills: Let Agents Design Agents
Minimalist 219 tok · · Q0
OpenRaiser/NanoResearch
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
Pragmatist 1.1k tok · · Q0
dtsola/xiaoyaosearch
小遥搜索,听懂你的话、看懂你的图,用AI找到本地任何文件。让搜索像聊天一样简单。XiaoyaoSearch: Understands your words, reads your images, finds any local file with AI. Making search as easy as chatting.
Pragmatist 5.0k tok · · Q0
agentscope-ai/OpenJudge
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
Minimalist 110 tok · · Q0
stevesolun/ctx
CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.
Skill Collector 3.4k tok · · Q0
qualixar/superlocalmemory
Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253
Skill Collector 14.2k tok · · Q20
guaardvark/guaardvark
The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agents on one GPU, driven from the Studio or by your coding agent (Claude Code, Cursor, Codex, OpenClaw) through MCP and skills.
Skill Collector 912 tok · · Q0
RobThePCGuy/Claude-Patent-Creator
USPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents, automated 35 USC 112 compliance checks, prior art search, diagram generation. GPU-accelerated with
Orchestrator 6.5k tok · · Q0
ThinkFlowLab/system1-agents
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
Pragmatist 2.9k tok · · Q0
inin-zou/codex-privacy-hud
OpenAI Privacy hackathon - Paris, 🏆 winning project
Pragmatist 4.7k tok · · Q10
sysevol-ai/CodeNib
Find source context and trace calls across languages in Claude Code, Codex and other MCP agents.
Pragmatist 9.0k tok · · Q15
kangise/ecommerce-ai-skills
Cross-border e-commerce AI knowledge base, read by people and installed by agents: 69 trilingual guides, 878 prompts, a 100-entity / 322-constraint ontology, and 9 skills as a Claude Code plugin or over MCP. Factual claims are dated and CI-
Pragmatist 538 tok · · Q0
vbcherepanov/total-agent-memory
Persistent local memory for AI coding agents — Claude Code, Codex CLI, Cursor, any MCP client. Temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. LongMemEval R@5 95.1%, LoCoMo 0.607, BEAM 1M 0.448. 74 M
Pragmatist 2.6k tok · · Q0
amos689/paper-preflight
Pre-submission integrity gate for LaTeX papers: every reference verified against real scholarly records. No LLM guessing.
Pragmatist 2.6k tok · · Q0
ariffazil/arifOS
Independent policy kernel for AI agents: judge before execute. F1–F13 floors, VAULT999 receipts. Not a model. Not a chatbot.
Skill Collector 8.7k tok · · Q5
ItMeDiaTech/rag-cli
Local Retrieval-Augmented Generation (RAG) plugin for Claude Code that combines Chroma db vector embeddings with intelligent info retrieval with Multi-Agent Framework (MAF) orchestration for context-aware development assistance. Uses Open S
Pragmatist 5.2k tok · · Q0
Thanatos9404/llmslim
Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
Pragmatist 2.6k tok · · Q0
lawrence3699/jev-style
Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.
Pragmatist 515 tok · · Q0
dshakes/distil
Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.
Minimalist 11 tok · · Q15
lucasmartins-ai/lcc
Compact coding-agent context without summarizing it away. Verbatim, offline, with a receipt and recall for every cut. CLI, MCP server, Claude Code plugin. MIT.
Pragmatist 2.6k tok · · Q0
newsbubbles/ismail
Ismail: A high bandwidth agentic interface. Includes Agentic DAW and Agentic VR stage with Evolvable Phone Interface. Have Claude or Codex produce and DJ music, jam with you, make sound effects and interactive soundscapes, movie scores, etc
Pragmatist 3.3k tok · · Q3
star-ga/mind-mem
Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.
Pragmatist 4.6k tok · · Q0
turtir-ai/kairos-context-keeper
Kairos: An autonomous development supervisor powered by Context Engineering. It provides a living memory and a contextual constitution for your projects to prevent AI context loss.
Pragmatist 2.9k tok · · Q0
Kromatic-Innovation/athenaeum
Open source knowledge management pipeline — passive recall, append-only intake, tiered compilation, configurable schemas
Minimalist 2.0k tok · · Q3
GiulioDER/RE-call
Memory that abstains instead of guessing: agent memory in a local SQLite file or your own Postgres, with a verdict, confidence and provenance on every hit, and a calibrated refusal when nothing clears the threshold.
Pragmatist 5.0k tok · · Q3
Pseudogiant-xr/Pseudolife-MCP
Persistent long-term memory for Agents — an MCP server with an associative memory bank, a canonical-fact cortex, sleep-like dream consolidation, and a web console. Not quite alive.
Pragmatist 10.1k tok · · Q5
lodsb/prax
A self-hosted library for the papers and web pages one person reads: hybrid search, a graph whose links cite their sentence, and an MCP interface for agents
Pragmatist 14.4k tok · · Q8
awsdataarchitect/voice-cloning-agentcore
An autonomous voice cloning agent powered by Amazon Bedrock AgentCore, Strands framework, and Nova Premier Model that captures your voice profile & synthesizes speech with intelligent tool execution.
Minimalist tok n/a · · Q0
YuhuanStudio/Yunshu
Fast local LLM / VLM inference engine for Apple Silicon (MLX). OpenAI- and Anthropic-compatible, lossless speculative decoding (DFlash2 / MTP), hybrid-model prefix cache with RAM/SSD tiers, native Claude Code / Codex / opencode support. Qwe
Minimalist 1.4k tok · · Q3
JayThibs/mats-workshop-2025-emergent-misalignment
MATS AI Safety Research Workshop - Claude Code setup with emergent misalignment research pipeline
Pragmatist 2.1k tok · · Q9
mariusCNN/sports-video-coach
Open-source sports video analysis and basketball analytics for Claude Code, Codex and AI agents. Video to coaching reports, clips, narration and explained MP4s; player/ball tracking, shot charts, training plans and optional OpenHoopVision,
Pragmatist 2.9k tok · · Q20
mariusDing/sports-video-coach
Open-source sports video analysis and basketball analytics for Claude Code, Codex and AI agents. Video to coaching reports, clips, narration and explained MP4s; player/ball tracking, shot charts, training plans and optional OpenHoopVision,
Pragmatist 2.7k tok · · Q20
nevenincs/vaultspec-rag
Semantic search for your vault and code, through the CLI or MCP. Inference runs on your GPU.
Orchestrator 12.6k tok · · Q20
nkllon/kiro-ai-development-hackathon
Code with Kiro Hackathon: AI-Powered IDE for Spec-Driven Development
Pragmatist 36.0k tok · · Q5
Bazza1982/HASHI
Local-first control plane for persistent AI agents—unifying identity, memory, tools, workflows, governance, and multi-channel access across HER v2, Claude Code, Codex, Gemini, and more.
Pragmatist 1.4k tok · · Q0
CaseyRo/mcp-stolperfalle
FastMCP server that captures and recalls experiential knowledge (Knowledge Units) for AI coding agents — a superset of the mozilla-ai/cq schema with strict-mode interop
Skill Collector 3.1k tok · · Q8
Sandeeprdy1729/timps-swarm
160 specialist AI agents for Claude Code, Cursor & Codex — one npm install puts them all into your IDE as MCP tools and parallel sub-agents. Local-first, BYOK, works offline with Ollama.
Orchestrator 9.7k tok · · Q0
Vironnimo/vbot
Your own AI agents, self-hosted: persistent agents with memory that work with you or on their own, in chat, real terminals, swarms, on schedules and by voice. Any model (subscriptions, API keys, local). Browser, desktop, CLI, Telegram, Disc
Skill Collector 3.8k tok · · Q20
Ybx-jp/thalamus
Federated graph memory for coding agents, with a trust model and measured utility loop.
Skill Collector 5.8k tok · · Q34
layersistem/brain-kit
Persistent memory + consolidation layer for Claude Code (and other agent CLIs). Local, plain-markdown, no API key.
Minimalist 32 tok · · Q0
lbruton/SessionFlow
Semantic search over Claude Code session transcripts. Recovers information lost to context compression.
Skill Collector 10.3k tok · · Q23
Ian-q/Carta
Carta is a Claude Code plugin that keeps your project docs honest — auditing for contradictions, embedding reference material into a searchable knowledge base, and surfacing the right context exactly when you need it.
Pragmatist 7.6k tok · · Q18
Parvathy-Raj/hallucination-firewall
MCP server that checks an AI agent's answer against its tool outputs before you see it: exact checks, NLI and an LLM judge, with block / annotate / rewrite policies
Pragmatist 5.0k tok · · Q0
markdorof/delphi-code
Let coding agents browse code across all your repos, offline
Pragmatist 2.7k tok · · Q0
sushiHex/mainframe-mcp
100% local knowledge and persistent memory for coding agents. GPU-accelerated hybrid search with source citations and a low VRAM footprint, powered by one shared MCP daemon.
Minimalist 2.2k tok · · Q5