100/100
parlant
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
◆ Curated from real-world signals
Find software
worth using.
Explore quality-filtered AI, SaaS and developer tools. No paid rankings, no endless noise—just useful software backed by public data.
19,788 tools reviewed · Public popularity signals · Refreshed continuously
Browse by focus
View all categories
Popular categories
100/100
X-AnyLabeling
X-AnyLabeling: A lightweight, efficient, and unified cross-platform desktop application for annotating text, image, video, point cloud and multimodal data, comb
100/100
AI-Research-SKILLs
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an
100/100
awesome-ai-engineering
🚀 A curated collection of AI engineering resources, roadmaps, tools, and projects covering LLMs, RAG, AI Agents, MCP, fine-tuning, evaluations, and production
100/100
TrendRadar
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平
100/100
kedro
Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines
Just landed
New AI tools
89/100
ShowAI
The evolving interface between humans and agents — Claude Code and Codex answer with interactive pages you can edit, keep and share.
89/100
ChatCrystal
Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.
90/100
sciclaw
Paired-scientist AI assistant for reproducible research — lightweight Go runtime, lifecycle hooks, manuscript integration, 12 baseline scientific skills. PicoCl
91/100
AICU-Graph
可扩展到各个领域的多 Agent 协作平台：自动分析任务，动态组建由不同角色组成的 AI 团队，协同完成复杂任务。
92/100
vllm-rlt
A vLLM-inspired inference engine for looped transformers, with loop-level scheduling and execution across composable stages
88/100
avplumber
A "gstreamer-like" C++ framework for ffmpeg/libav graphs with support of async processing and lock-free queue
87/100
PurePoint
Turn your agents into your point guard, while you coach and draw up the plays.
87/100
DevProjex
Build safe, token-efficient codebase context for LLMs, AI chats, and coding agents — local-first GUI, TUI, CLI, and a read-only MCP server with Smart Ignore, se
87/100
AGmind64
Self-hosted LLM/RAG stack in one command — AMD Strix Halo / x86_64 (ROCm/Vulkan, Docker Compose)
87/100
aibuilder-json
Enterprise-grade FastGPT workflow JSON generator - Works with Claude Code, OpenClaw, Costrict.ai, Trae and any skill-based AI platform
87/100
Quillan-Ronin
Quillan-Ronin - a sovereign mini Software 3.0 runtime on Universal BitNet 1.58-bit logic and a 9B EGGROLL Swarm. v5.4.0-oni features a 34-expert council (C1–C34
87/100
dive
Dive is a secure, local-first desktop client for LllamaCCP, LmStudio, Ollama, Pi agentic AI and Cloud. Features an ultra-compact offline RAG engine for indexing
87/100
fastapi-agent-blueprint
FastAPI backend blueprint for AI agent apps: DDD, SQLAlchemy, Taskiq, admin UI, RAG infra, and Claude/Codex collaboration harness.
87/100
unmute
Voice agents in YAML, compiled to Pipecat or LiveKit. Production code you own, deployed anywhere.
87/100
Global-News-Intel-Platform
AI-powered geopolitical news intelligence platform. Ingests 100K+ daily events from GDELT, stores in MotherDuck (DuckDB), orchestrates with Dagster, and feature
87/100
surface
Portable, always-fresh docs for agents and humans. A Surface hub is a conformant OKF concept; Surface adds the freshness OKF leaves out - it fails the build whe
87/100
fortemi
Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cp
87/100
montycat-mcp
Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Cursor, Codex, and any MC
87/100
context-engineering
🧠 Stop building AI that forgets. Master MCP (Model Context Protocol) with production-ready semantic memory, hybrid RAG, and the WARNERCO Schematica teaching ap
87/100
roast-my-design-system
AI design system scanner + mcp server. Scores repos 0-100, writes fix prompts. 27K+ npm downloads.
87/100
OfficeAgent.NET
Structured Word, PowerPoint, and Excel automation for .NET and coding agents, with validated plans, MCP, tracked changes, and SharePoint
87/100
Graft
Your coding agents forget. Graft doesn't. Persistent local memory that brings back fixes, decisions and project knowledge when they matter — across Claude Code,
87/100
ctxpipe
Git-backed context for coding agents. Your code, tickets, docs and incidents become Markdown in one repo you own, refreshed on every push and served to Claude C
87/100
platform
A modern, sovereign AI backend for products and enterprise deployments.
87/100
react-frontend-skills
Production-grade AI agent skills for React 19, Next.js 16, TypeScript 7, testing, data, UI, and frontend architecture—ready for Codex, Claude Code, Cursor, Pi,
87/100
AutoMaintainer
An Always-On Autonomous AI Software Engineering Team built with LangGraph, FastAPI, and Next.js that operates natively within your GitHub repositories.
87/100
slop-grader
Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.
87/100
awesome-foundry-nextgen
Hands-on labs for Microsoft Foundry - Azure's unified PaaS for enterprise AI. Notebooks + Bicep covering provisioning, agents (incl. hosted Copilot SDK + REST),
87/100
webjs
WebJs is an AI-first full-stack JavaScript web components framework. You get production-ready architecture from your very first prompt.
87/100
hadron
A native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an automatic merge gate