Developer Tool / AI Infrastructure
Open-source local compute fabric for AI agents. It runs a single-node K3s stack through Docker Compose, provisions isolated Ubuntu sandboxes, and exposes native MCP support for local agent workflows.
The page clearly describes an AI-adjacent developer product with a concrete purpose: local infrastructure for autonomous agent execution, orchestration, and MCP tool discovery. The README shows setup steps, prerequisites, DNS guidance, Claude Desktop integration, and API access, which is enough for a useful public listing.
The crawl does not show the code’s runtime maturity, release history, screenshots, or whether the project is actively maintained beyond a few commits. It also does not clearly spell out all supported agent runtimes, model providers, or example workflows beyond Claude Desktop and a tools/list check.
Last evaluated 31 days ago. Current rank #323. 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.
