Kanzo
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…
AI tools similar to Inference optimisation skill — Agent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any…
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…
Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps…
An on-device AI agent for Android that operates apps and the web to get things done for you.
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By…
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…
Infrastructure for continually self‑improving agents
Train open models with RL inside real agent harnesses
Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable…
Use LLMs to learn a new domain, not skip past it
Put thousands of live DOM nodes on an infinite canvas: the GPU draws them, an editor selects, moves and resizes them…
open source rust gateway to trace every LLM call
Can AI agents rebuild websites through browser exploration?
22 MB vision model - description, boxes, masks, OCR, forms
Compile organizational policy into verifiable decision training data.
Know which AI to run on your own computer
🔥🔥 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…
Open-source, on device alternative to Claude Cowork and ChatGPT
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No…
llama.cpp fork that abliterates at inference
Better judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.
Generative Fill, Remove object, Generative Expand and Text to Image for PhotoCraft and GIMP 3. Free, local, on your own…
Xiryn — the open-source personal agent. Does everything Muse, Grok Bot and Dots do, on your own computer: each agent…
Open-source Grok Bot alternative. Choose your own model and sandbox.
World's first open-source enterprise world model.
MiMo Code: Where Models and Agents Co-Evolve
OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
OSS on-device voice dictation for macOS with no model to download
Guardrails take an 8B model from 53% to 99% on agentic tasks