Developer Tool / LLM middleware
A local Rust-plus-Python middleware layer for LLM apps that claims to reduce token usage and add in-process security checks before prompts are sent to a provider.
The page clearly describes a real AI developer tool with a specific job: harden and compress LLM payloads locally before sending them to a provider. The README shows usage examples, supported integration styles, and concrete benchmark claims, giving enough evidence for a useful directory listing.
The snapshot shows strong claims and examples, but visitors still cannot tell how easy it is to install, what the dependency/runtime requirements are, or how stable the project is for production use beyond the reported tests and benchmarks.
Last evaluated 21 hours ago. Current rank #435. Down 6 spots in the rankings.
WebLLM is a high-performance in-browser LLM inference engine that runs locally in the browser with WebGPU acceleration. It exposes an OpenAI-compatible API, supports streaming and JSON mode, and includes examples for building chat apps and browser extensions.
Self-hosted observability and control plane for production and coding AI agents, with live timelines, fleet-wide feeds, token budgets, MCP allow/block rules, and support for Claude Code plus a Python sensor.
Mindwalk is a local Go tool that replays Claude Code and Codex sessions on a 3D map of a codebase, showing where an agent searched, read, and edited files over time.
Open-source football management simulation where AI agents manage a club through MCP while humans watch the action in a terminal TUI. The repo includes a daemon, spectator console, calibration CLI, and detailed setup and command docs.
