📝 Markdown and HTML renderer for Svelte 5 — built for streaming AI agent output from Claude Code, ChatGPT, and agentic workflows. XSS-safe defaults, token caching, TypeScript types.
Pure-Rust, no_std collection of 30+ compression/decompression codecs (deflate, gzip, zlib, zstd, brotli, lzma/xz, lz4, bzip2, RAR, StuffIt, LHA, ARC, and more) behind one uniform streaming trait — each gated by its own Cargo feature. 100% safe (forbid(unsafe_code)), zero runtime deps.
Production-ready LLM API translation layer for Python — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome!
Project Graphorin is a TypeScript framework for personal AI assistants and long-living agents with rich memory, durable workflow, and observability out of the box.
A composable framework for building reliable LLM agents on a harness you fully control. The same code runs the agentic loop on every model tier, local 4B to frontier with tool-call healing, verification, and durable crash-resume, on a typed 12-phase engine where every step emits an event you can hook into. Effect-TS, MCP-native, MIT
A secure JavaScript sandbox designed for safe AI agent code execution. Protects against code injection, prototype pollution, and sandbox escapes. The security layer that makes AI-generated code safe to run.