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.
19,670 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
90/100
loopcut
Loopcut: an AI agent that works inside Blender. A fork of Blender (GPL).
90/100
walrus-memory
A portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.
88/100
bloomery
Hybrid GPU + CPU inference for mixture-of-experts models, written in Rust down to the CUDA kernels. A drop-in llama-server.
90/100
stalemap
Tell your coding agent which dependencies changed after its training cutoff. Diffs types and changelogs, writes a short block into AGENTS.md / CLAUDE.md.
93/100
rs-graph-llm
High-performance framework for building interactive workflow systems in Rust. Designed for complex workflows and multi-agent systems
96/100
sionna
Sionna: An Open-Source Library for Research on Communication Systems
L2
80/100
LTX-2.3 Video [Turbo]
Generate video + audio with LTX-2.3 (22B) on free ZeroGPU
L2
80/100
LTX-2.3 Turbo
Generate video + audio with LTX-2.3 (22B) on free ZeroGPU
AV
80/100
AI Video Studio
AI-powered video creation with avatars, voice cloning & TTS
L2
80/100
LTX-2.3 Video [Turbo]
Generate video + audio with LTX-2.3 (22B) on free ZeroGPU
AS
80/100
Angle Studio
96 camera angles from one image — ZeroGPU
PS
80/100
Pix2Pix - Satellite Image to Map
Satellite to map conversion using Pix2Pix GAN
AV
80/100
Anima V1 ZeroGPU Demo
Demo of Circlestone Labs's new Anima V1 mode
P·
80/100
Poetic · 诗情画意
写一首诗，化作画、朗诵配乐与会动的小影片 — all small open models
TC
80/100
The Compliment Forest
Turn a worry into a grounded, illustrated path forward.
CC
80/100
Cryptid Cannon
Fire the cannon, summon a random absurd cryptid on klein 4B
CC
80/100
Cryptid Cannon
Fire the cannon, summon a random absurd cryptid on klein 4B
DA
80/100
DanbooruSearch
基于语义匹配的 Danbooru 标签搜索引擎，支持多维匹配、智能分词与共现关联推荐。
AV
80/100
Anima V1 ZeroGPU Demo
Demo of Circlestone Labs's new Anima V1 mode
AV
80/100
Anima V1 ZeroGPU Demo
Demo of Circlestone Labs's new Anima V1 mode
F2
80/100
FLUX.2 klein 4B — Build Small Starter
Text-to-image, editing, and your own LoRA on klein 4B
AC
80/100
Anima ControlNet VACE Depth
Anima depth-conditioned image generation via VACE ControlNet
QI
80/100
Qwen Image Flash
4-step DMD2-distilled text-to-image with Qwen-Image-Flash
QI
80/100
Qwen Image Flash
4-step DMD2-distilled text-to-image with Qwen-Image-Flash
G·
80/100
Genoria · Cosmos3-Super Text2Image
Text-to-image demo · NVIDIA Cosmos3-Super 64B (NVFP4)
CF
80/100
Chinese Female Body · Qwen Image LoRA
Realistic Chinese portrait LoRA demo for Qwen-Image
ML
80/100
Missing Link Studio — AI Image Generation & Editing Workspace
Generate, edit, and direct AI images — GPT & SDXL, video, 3D
PI
80/100
POCKET-Image Studio
Perfect text in any language, in any image
CA
80/100
Claims Assessment SLM
Failure claims assessment using fine-tuned GPT-2 Large
HU
80/100
HuggingClaw
Free always-on AI assistant, no hardware required