Trending AI repositories

axocoatl/

axocoatl

Agentic runtime in Rust — persistent, supervised agents. Self-hosted, local-first, zero telemetry. Apache 2.0.

fjgbue/

claude-delegator-deepseek-mcp

MCP server: delegate heavy-token tasks from Claude Code to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Mix providers per task, cost receipt on every call. Zero dependencies.

NullLabTests/

software-periodic-table

A finite ontology of 115 recurring software elements and a composition framework for LLM-based coding agents

UIseries/

ai-robot

RK3506 Voice Robot An embedded AI voice assistant running on the Rockchip RK3506 development board. Pure C, single-threaded event loop, zero dynamic memory allocation.

momozi1996/

momo-code

MOMO CODE — AI coding agent that evolves with you

tathagat22/

plumb-mcp

Local Figma MCP server with no REST rate limits, no metered tool-call quotas, and a verification loop. Drop-in alternative to Figma's Dev Mode MCP and Framelink for Claude Code, Cursor, Windsurf — works on every plan including Free.

tonnode/

mcp

TON MCP server for Claude, ChatGPT, Cursor, Codex and any MCP client — liteserver queries over native ADNL: balances, account state, transaction history, get-methods. Private & archive endpoints supported

aaronnat23/

disp8ch

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or cloud models

bolivestilo/

Homekit

Homekit gives any AI agent direct, physical control over Apple Home. Flip lights. Lock doors. Read sensors. Through a single open interface.

k4cper-g/

agent-ctrl

Desktop automation CLI for AI agents. Fast native Rust CLI.

Automations-Project/

VSCode-Perplexity-MCP

Perplexity AI search, reasoning, research, and compute - MCP server, dashboard, and multi-IDE auto-config for VS Code.

drumih/

turbo-fieldfare

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

band-ai/

codeband

A coding tool to orchestrate multiple coding agents

aduermael/

wb

macOS 26+ browser CLI for agents: persistent sessions, compact JSON, screenshots, clicks/forms, JS eval, and live preview in under 2 MB.

sshwarts/

skillscript

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

S40911120/

recensa

Self-hosted web viewer for Claude Code session transcripts — read, search, replay, and audit every session you have ever run

HiAi-gg/

docsmint

DocsMint - self-hosted AI-native knowledge workspace with semantic search, GraphRAG, REST, CLI, SDK, and MCP.

apisec-inc/

AI-Surface

Find and govern AI attack surfaces in application code at PR time. Free, OSS, runs offline.

langgenius/

mosoo-agent-driver

Runtime-neutral driver for Claude Code, Codex, and ACP. Compatible with Claude Managed Agents (CMA) API.

baldaworks/

callee

Markdown-defined provider-backed agents and deterministic workflows for ACP runtimes.

MemTensor/

memmy-agent

One Agent. One memory. Shared by every AI. 🍙

DevOpsAIguru123/

awesome-agentic-devops

Curated + scored map of official MCP servers and agents for DevOps, Cloud, SRE, and Platform Engineering — every entry rated on production access, approval gates, and audit evidence.

OpenCPIL/

prima.cpp

[Official] prima.cpp: Fast 30-70B LLM inference on heterogeneous and everyday home devices

niki914/

agentic-nexus

Takeover your voice assistant with powerful agent

rudrankriyam/

Google-Health-CLI

Unofficial Google-Health-CLI for the Google Health API, written in Go

kostyay/

pi-k-excalidraw

Native Excalidraw diagram preview tool for pi — draw and save diagrams from the agent with a live glimpse webview.

EndymionLee/

PilotBrowseMCP

A browser runtime that lets AI agents control your real Chrome browser via MCP. Agents can explore websites, generate operation manuals, and reuse them to save tokens. AI操控你的真实浏览器。

DFKHelper/

token-goat

Token burn reducer and focus keeper for Claude Code, Codex, Copilot, Gemini CLI, and more: surgical read hints, PDF/Office/CSV/markdown file interception, 160+ filter & interception rules, compact manifest injection, image shrinking, cache and compact skills, cache MCP calls, prompt injection protections, and much more.

Bike4Mind/

bike4mind

The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.

escoffier-labs/

brigade

Your agents run loops. Brigade keeps the receipts. Local control plane: share MCP, tools, and memory across harnesses; prove with file receipts; improve only from real exit codes. No daemon, no lock-in.