91/100
opengeni
Open, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed
Curated collection
Best AI Tools Directory
Compare 5,036 quality-filtered AI tools—LLMs, coding agents, image generators, and automation—using public popularity, activity, and licensing data.
Explore quality-filtered AI tools for chat, coding agents, image generation, RAG, and automation. Rankings use public popularity and project activity—not paid placements.
Compare your options
Popular comparisons
- gpt-researcher vs note-gen
- note-gen vs agenticSeek
- note-gen vs best-of-ml-python
- Langchain-Chatchat vs note-gen
- note-gen vs PentestGPT
- note-gen vs PocketFlow
- note-gen vs inkos
- gpt-researcher vs agenticSeek
- gpt-researcher vs best-of-ml-python
- gpt-researcher vs Langchain-Chatchat
- gpt-researcher vs PentestGPT
- gpt-researcher vs PocketFlow
91/100
nanzi-ai-agent-platform
🚀 开源企业级多智能体平台与 ChatBI 数据洞察平台。支持多 Agent 协作、RAG 知识增强、物理数据源直连与安全沙箱执行、Redis 长期记忆引擎，并集成多模态 EmbedChat 挂件
91/100
dev-machine-guard
Scan your dev machine for AI agents, MCP servers, IDE extensions, and suspicious packages - in seconds.
91/100
pi-automode
Think Claude Code's auto mode but for pi (and oh-my-pi). Selectable model, sensible defaults.
91/100
LZ-litchi
LZ-Litchi（荔枝软件开发平台） 是一个基于 JDK 21、SpringBoot 3、Vue 3、VbenAdmin 构建的现代化企业级开发平台，采用前后端分离架构，内置 RBAC 权限管理、多租户、工作
91/100
NeMo-Relay
Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.
91/100
autopilot
Autopilot (previously Kimiflare) is an open source harness inspired by claude code. works with open router
91/100
ai-toolkit
Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigrav
91/100
sm64ds-decomp
From-scratch, byte-matching decompilation of Super Mario 64 DS into C/C++, with a live progress atlas and matching tools.
91/100
skill-conductor
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure
91/100
Goida-AI-Unlocker
🛡 Установщик разблокировщика зарубежных AI-сервисов (и не только) для России 🌍
91/100
cnllm
Python toolkit for Chinese LLMs, with flexible batch capacity, structured real-time visulization and automated accumulation for streaming, and explicit feedback
91/100
awesome-production-agentic-systems
A curated list of awesome open source libraries to deploy, monitor, version and scale agentic applications and systems
91/100
yantrikdb-server
Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Apache-2.0, ships as l
91/100
easy-data-x-ai
《Easy Data x AI》是一门面向所有 AI 爱好者的数据与 AI 基础入门课程。通过双轨学习路径，从数据驱动视角学习构建 AI Agent。
91/100
agentsecrets
Zero-knowledge credentials infrastructure built for AI agents to operate, not just consume.
91/100
LiveMarkdown.Avalonia
High performance, real-time markdown renderer for AI/LLM
91/100
generative-ai-cdk-constructs-samples
This repo provides sample generative AI stacks built atop the AWS Generative AI CDK Constructs.
91/100
pyvespa
Python API for https://vespa.ai, the open big data serving engine
91/100
Warden
This is a fork of the https://dockbox.dev project I made
91/100
claude-command-center
Manage and orchestrate your Claude Code, Codex, Cursor, Antigravity, Kimi, Grok, Devin, Droid sessions on your Machine. Spawn in parallel, ship in parallel. Ope
91/100
Lilly
Bosnian-first offline assistant: type, speak, and snap street text → English. FastAPI app + Kaggle-trained listen/read models. Fail-stop training.
91/100
ScienceAgentBench
[ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
91/100
agentsmith
Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.