Developer Tools
SDKs, inference engines, data pipelines, monitoring, and AI infrastructure. 478 releases.
478 releases
Open ↗verifiers
verifiers is a library from Prime Intellect for creating environments to train and evaluate large language models.
Open ↗Miles
Since Week 37 2026: Miles, RadixArk's reinforcement learning framework for LLM and VLM post-training (forked from and…
Open ↗Google Maps Scraper Kit
Google Maps Scraper Kit is an open-source lead-generation scraper that runs locally in Docker with no Google Maps API…
Open ↗TrenTorch
TrenTorch is a free website of ML practice problems in which users write the code for machine learning components…
Open ↗DeepInfer
DeepSeek open-sourced the inference framework behind its production services, created 16 October under Apache 2.0.
Open ↗Colab in Google AI plans
Google announced on 22 September that Google AI subscribers now get premium Google Colab benefits, including priority…
Open ↗Free Claude Code
Since Week 30 2026: the proxy now lists 61 providers and 11 coding agents, adding Cline, Hermes, DeepSeek Harness, Grok…
Open ↗claude-swap 0.27
A Python command-line tool, cswap, that switches between several Claude Code accounts without logging out, rotates…
Open ↗OneTrainer
Since Week 14 2025: this open-source GUI and command-line trainer for diffusion models has added support for Chroma…
Open ↗LLM Wiki v2
A local Python app that files dropped .txt, .md and .pdf documents into a wiki of plain Markdown notes in ~/llm-wiki,…
Open ↗Impeccable v4.5
A design skill set, at impeccable.style, that gives coding agents a design vocabulary through commands such as typeset,…
Open ↗YouTube Agent Skill
Eleven Claude skills for running a YouTube channel: scripts built from 21 hook formulas with the hook scored first,…
Open ↗Logo Design Skill
An Agent Skills package, launched 26 September, that has Claude, Gemini CLI, Codex, Cursor or Copilot work through logo…
Open ↗Archify 3.0
Since Week 36 2026: Archify, an agent skill for Cursor, Claude Code, Codex CLI and OpenCode that turns code or a system…
Open ↗Olmo-core 3
Version 3 of Ai2's open training library, released 1 October with a rebuilt mixture-of-experts system that scales to…
Open ↗Awesome Opus 5.5 Videos
A collection of 475 prompts behind viral videos people made with Claude Opus 5.5 (covered in week 40), mostly Canvas,…
Open ↗Altar
A compressed, open-weight derivative of GLM-5.3, shrunk from 1.51TB to 328GB, a 78.2% reduction retaining 168 of 256…
- Open ↗
Inspo
An MCP server giving coding agents a reference archive of real production websites to look at before building UI.
- Open ↗
God's Eye View
An open-source browser globe that puts live aircraft, ships, satellites, earthquakes, traffic and public cameras on…
- Open ↗
Needle 3
Since Week 33 2026, when this archive covered Needle 2.
- Open ↗
Toward Recursive Self-Improvement
Z.ai describes putting GLM-5.3 to work as an infra agent that built and optimised the production inference stack now…
- Open ↗
edge0
A streaming mixture-of-experts inference framework for Apple Silicon on MLX, combining SSD expert offload for bounded…
- Open ↗
OUI-1
A diffusion model fine-tuned to generate UI screens in openui-lang, a declarative markup language, from plain-language…
- Open ↗
Recordly v1.4.0
Since Week 18 2026, and that entry recorded no version at all.
- Open ↗
Headroom v0.37.0
Context compression for agents, shrinking prompts, tool outputs, logs, RAG chunks and files before they reach the model.
- Open ↗
TrenTorch
A deep learning framework built on NumPy alone, no PyTorch or TensorFlow anywhere, structured as 20 progressive modules…
- Open ↗
Uncensored Local AI Multiplatform v2.0.0
A Flutter app running uncensored open-source GGUF models fully offline across Android, iOS, Windows, macOS and Linux…
- Open ↗
ComfyUI-VDN-H3
Ports VDN into ComfyUI for MiniMax-H3, patching attention at runtime - exact softmax for nearby frames, a constant-cost…
- Open ↗
VDN
Video DeltaNet is a hybrid attention design pairing sliding-window softmax attention with a linear-attention branch,…
- Open ↗
TimesFM-3
A 330M decoder-only transformer for time-series forecasting pretrained on over a trillion time points, and the first in…