Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Repository Index
47,133 repositories indexed
1–15 of 15 · Most stars
#1 Persistent memory for AI coding agents based on real-world benchmarks
🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
- data-format
- llm
- serialization
- tokenization
Your One-Stop Publication Workbench
- office
- productivity
- electron
- offline
Android Reverse-Engineering Workbench for VS Code
- apktool
- apk-decompiler
- apk-editor
- smali
The ESP32-S3 bench guide as a React app: live pinout, lessons with interactive simulators, a code reader for the esp-labs firmware, and the bench log. In 11 languages.
Automated Chrome tracing for benchmarking.
- benchmark
- chrome
Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex and Pi.
Feel how fast a local LLM runs before you buy the hardware
Local multi-AI desktop workspace with official website panels, shared prompts and group collaboration.
- ai-chat
- chinese
- desktop-app
- electron
A VSCode Extensions that can download and launch Minecraft.
An async / await friendly debugging client for chrome
Blazing fast 2D renderer for the web: 2-4x faster than the most popular one, at a ninth of its size. Verified in an open benchmark.
TranslatedOpenMinutes · Voice recorder workbench: import · transcription · AI categorization · search and review of MemoTalk S1 recordings (open-source implementation of Floatboat Workbench)
- ai-classification
- floatboat
- react
- speech-to-text
Benchmark recording of an ember app with running with 2 versions of Ember.