#Apache 2.0

hashgraph-online

hol-guard

★ 845

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

amaiya

onprem

★ 845

A toolkit for applying LLMs to sensitive, non-public data in offline or restricted environments

cyrusagents

cyrus

★ 843

The Claude Code background agent for Linear, Slack, Github, GitLab etc. you deploy anywhere. Supports Codex, Cursor, Gemini, and Opencode harnesses too.

golf-mcp

golf

★ 840

Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents

ardanlabs

kronk

★ 839

Your personal engine for running open source models locally. Use Go for hardware accelerated local inference with llama.cpp and whisper.cpp directly integrated into your Go applications. Kronk provides a high-level API and a model server.

scaleapi

llm-engine

★ 839

Scale LLM Engine public repository

flosell

trailscraper

★ 838

A command-line tool to get valuable information out of AWS CloudTrail.

Ayanami0730

deep_research_bench

★ 838

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

gotonote

Autopilot-Notes

★ 838

Autonomous-driving notes that break down key concepts from each module and summarize leading industry solutions, for the author and other readers; covers deep learning, autonomous driving, BEV, Transformer, ADAS, CVPR, Tesla AI Day, large language models, ChatGPT and more.

llama-farm

llamafarm

★ 836

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

gotempsh

temps

★ 835

AI-native open-source alternative to Vercel + Sentry + PostHog + Pingdom + Resend + E2B. 440+ CLI operations with drop-in skills for Claude Code, Codex & OpenCode — deployments, analytics, session replay, error tracking, OpenTelemetry, email, sandboxes & AI gateway in one self-hosted Rust binary.

BiomedSciAI

causallib

★ 835

A Python package for modular causal inference analysis and model evaluations

BryceWG

BiBi-Keyboard

★ 832

BiBi Keyboard: an LLM and ASR voice-input method keyboard app for Android, built with Kotlin.

AVIDS2

memorix

★ 829

Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.

qwen-code-dev-bot

oh-my-cli

★ 828

A minimal autonomous code-agent CLI built with Qwen Code

AgnosticUI

agnosticui

★ 827

AgnosticUI Local (v2) is a CLI-based UI component library that copies components directly into your project. Works with AI tools, agent-driven UIs, and prompt-ready workflows.

jwangkun

claude-for-financial-services-cn

★ 827

63 Claude Skills built for A-share financial professionals, deeply adapted from Anthropic's official claude-for-financial-services for the domestic Chinese market, now open source.

suyoumo

ClawProBench

★ 824

ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

weirdmachine64

GhidraGPT

★ 824

Integrate LLM models directly into Ghidra for AI-enhanced reverse engineering.

astra-vision

MonoScene

★ 822

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image