Developer Tool / AI Proxy / Context Management
Open-source transparent proxy for coding agents that preserves full conversation history on disk while selectively deciding what the model reads. Supports OpenAI-compatible, Anthropic Messages, and OpenAI Responses APIs, with setup docs, engine-specific configs, and benchmark claims for long-horizon agent sessions.
The page clearly describes a real AI developer tool with a specific job: managing long agent histories through a transparent proxy and recalled memory. The README shows install steps, supported backends, example configs, API compatibility, and measured results, giving enough evidence for a useful public listing.
The crawl does not show the full benchmark methodology or how well it behaves across different workflows beyond the listed examples. It also is not obvious from the snapshot how much setup is needed for each engine in practice, or what failure modes to expect when a backend does not support saved state.
Last evaluated 33 hours ago. Current rank #882. Down 3 spots in the rankings.
A Rust Blu-ray disc analyzer that reimplements BDInfo for BDMV folders and ISO images, with CLI, desktop, and browser/WASM front ends.
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.
An open-source MCP and CLI tool that lets AI agents read and control the iOS Simulator, build and test Xcode apps, and handle common iOS interactions with a compact screen representation.
Open source inference engine for agents that self-tunes on the user’s hardware to run open models faster, with desktop app support and one-click connections to popular agents.
