Developer Tool / AI Memory / Agent Infrastructure
A governed memory runtime for AI assistants with typed storage, policy checks, audit logging, tenant isolation, and hybrid retrieval. The repo includes a backend API, worker jobs, SDK examples, architecture docs, and eval harnesses.
The page clearly describes an AI-focused infrastructure product, not a vague concept. The crawl shows a working repository with a concrete stack, stable API/SDK claims, quickstart instructions, architecture docs, eval cases, and multiple components aimed at builders.
The snapshot does not show live product results, screenshots of the UI, deployment status, or how the system performs on real workloads. It’s also hard to tell from the crawl how much is already usable versus still under active development.
Last evaluated 25 days ago. Current rank #641. Down 3 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.
