WebsiteBench
Can AI agents rebuild websites through browser exploration?
AI tools similar to Langfuse AI Gateway — open source rust gateway to trace every LLM call
Can AI agents rebuild websites through browser exploration?
An on-device AI agent for Android that operates apps and the web to get things done for you.
Compile organizational policy into verifiable decision training data.
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By…
Self-hosted, sharable kanban for humans and agents. One 4.5 MB binary, 4.5 MB of RAM, 10 to 60 tokens per agent reply…
🔥🔥 The extremely fast inference engine for decision model
AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models - system prompts, AGENTS.md…
Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No…
Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps…
Better judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.
A toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus…
Xiryn — the open-source personal agent. Does everything Muse, Grok Bot and Dots do, on your own computer: each agent…
Infrastructure for continually self‑improving agents
Open-source Grok Bot alternative. Choose your own model and sandbox.
World's first open-source enterprise world model.
Train open models with RL inside real agent harnesses
MiMo Code: Where Models and Agents Co-Evolve
OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable…
3D modeling in Python, built for LLMs.
maxxing the ability to run different LLMs on the smallest devices possible
Turn a photo into a 10-second video — free, no GPU queue
22 MB vision model - description, boxes, masks, OCR, forms
Open-source risk and fraud decisioning platform
RAG over GitHub issues, with a hand-reviewed eval set and an audit of the judge itself. Reports the interval, not just…
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with…
3D objects, each with the Python program that builds it
Interactive Three.js 3D scenes from a prompt
managed inference powered by self-hostable stack
Open-source, on device alternative to Claude Cowork and ChatGPT