7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.
Repository Index
47,133 repositories indexed
1–24 of 171 · Most stars
:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.
Carbon Language's main repository: documents, design, implementation, and related tools. (NOTE: Carbon Language is experimental; see README)
- programming-language
- carbon-lang
- compiler
- cpp
A SQL database in Rust: SQLite-compatible, now also speaking Postgres (experimental). The LLVM of databases.
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
- notebooks
- python
- data-science
- machine-learning
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
- ai-research
- autonomous-agent
- claude-code
- codex
FFmpeg for browser, powered by WebAssembly
🦉 Data Versioning and ML Experiments
- data-science
- machine-learning
- reproducibility
- data-version-control
Image augmentation for machine learning experiments.
- image-augmentation
- machine-learning
- augmentation
- deep-learning
Open-source feature management platform
- feature
- feature-toggle
- unleash
- feature-flags
WebRTC, WebRTC and WebRTC. Everything here is all about WebRTC!!
- webrtc
- webrtc-demos
- webrtc-experiments
- webrtc-samples
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
- machine-learning
- experiment-track
- deep-learning
- keras
[deprecated in favor of https://microsoft.github.io/react-native-windows/] React Native for macOS is an experimental fork for writing desktop apps using Cocoa
mawww's experiment for a better code editor
- text-editor
- c-plus-plus
- console-application
- kakoune
Tool for real-time visualization, monitoring and collaborative analysis of AI/ML experiments and live data. Supports Python, PyTorch/Torch, NumPy, TensorFlow/Keras https://visdom.dev
Open Source Feature Flags, Experimentation, and Product Analytics
- abtesting
- statistics
- abtest
- experimentation
[EXPERIMENTAL] Graceful morphing effects for UILabel written in Swift.
Playing Pokemon Red with Reinforcement Learning
Flagsmith is an open-source feature flag platform with remote config, experimentation, and self-hosted or cloud deployment options.
- feature-flags
- continuous-integration
- remote-control
- ci
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
Experimental, scalable, high performance HTTP server
- lwan
- http
- c
- library
Experimental PlayStation Vita emulator
💥 Highly experimental plugin that completely replaces the UI for messages, cmdline and the popupmenu.
- neovim-lua-plugin
- neovim-plugin
- neovim-ui
- neovim
Litmus helps SREs and developers practice chaos engineering in a Cloud-native way. Chaos experiments are published at the ChaosHub (https://hub.litmuschaos.io). Community notes is at https://hackmd.io/a4Zu_sH4TZGeih-xCimi3Q
- chaos-engineering
- kubernetes
- chaos-experiments
- cloud-native