#AI Agents

perplexityai

numbat

★ 1,098

Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.

Toni-SM

skrl

★ 1,098

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

KevinLiss

ApeAdmin

★ 1,098

Apeadmin 面向现代AI应用打造的Python后台管理框架，基于 FastAPI+Vue3 设计100%开源，内置 RBAC 权限管控、审计日志等企业级基础能力。框架集成 MCP‑SSE 网关，具备强大插件生态完整，帮助开发者快速搭建兼具业务管理与 AI 工具输出能力的应用。

RUC-NLPIR

Arbor

★ 1,096

A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.

us

crw

★ 1,096

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.

bubblelabai

BubbleLab

★ 1,096

Open-core workflow engine powering Bubble Lab — and fully runnable, hostable, and extensible on its own.

LycheeMem

LycheeMem

★ 1,094

Lightweight Long-Term Memory for LLM Agents.

langchain-ai

agent-inbox

★ 1,093

📥 An inbox UX for interacting with human-in-the-loop agents.

flopperam

unreal-engine-mcp

★ 1,090

This MCP is now owned by Aura! Please try out the most intelligent AI agent for Unreal Engine at https://www.tryaura.dev/?utm_source=youtube&utm_medium=video&utm_campaign=flop

obot-platform

obot

★ 1,087

Complete AI Governance Platform from Obot AI

LucasAlegre

sumo-rl

★ 1,087

Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with Gymnasium, PettingZoo, and popular RL libraries.

agi-brain

xuance

★ 1,087

XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

yding-git

personal-edge-proxy

★ 1,087

A practical multi-inbound, multi-outbound personal proxy setup with Xray, Hysteria2, REALITY Vision, WARP and optional static SOCKS5 routing.

NirDiamant

Agent_Memory_Techniques

★ 1,085

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.

andrepimenta

claude-code-chat

★ 1,085

Beautiful Claude Code Chat Interface for VS Code

tigerowo

infinite-canvas

★ 1,083

开源 AI 创作工作台，集成无限画布、Agent、导演台、全景图、AI 生图、图片编辑、视频生成、画布编排等，兼容 OpenAI 接口及多种 API 服务

tigicion

dao-code

★ 1,083

Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.

asklokesh

loki-mode

★ 1,083

Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 8 quality gates.

cisco-ai-defense

mcp-scanner

★ 1,083

Scan MCP servers for potential threats & security findings.

agents-io

PokeClaw

★ 1,083

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.