Developer Tool / API Proxy / Caching
Cachet is a local semantic cache for LLM APIs that sits in front of OpenAI- or Anthropic-compatible endpoints and serves repeated or rephrased requests from cache. It includes a dashboard for hit rate and estimated savings, supports streaming responses, and is implemented as a single Rust binary.
The page clearly describes a real AI-adjacent developer tool with a specific job: transparent semantic caching for LLM API calls. The crawl shows enough detail to understand how it works, how to install it, how to point an app at it, and what problem it solves. It also shows concrete evidence of features like a local-only matching layer, dashboard, Docker support, and compatibility with OpenAI/Anthropic-style APIs.
The snapshot does not show any release history, test coverage, benchmarks, or maintenance signals beyond a few commits. It also leaves open how well the semantic matching performs in practice, beyond the author’s examples and threshold description.
Last evaluated 2 days ago. Current rank #300. 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.
Browser extension that scans pastes for credentials and PII before they reach LLM chat sites, with local on-device inference and no network calls.
Open-source runtime for multi-agent AI systems with job scheduling, DAG orchestration, shared memory, tool execution, and real-time observability.
