Developer Tool / AI Agent Infrastructure
A service-boundary-aware coordination layer for heterogeneous LLM code agents via MCP. It combines versioned Markdown documents, pub-sub notifications, diff-aware updates, and a web dashboard for browsing, search, and AI chat.
The page clearly presents a real AI developer tool with a specific purpose: coordinating LLM code agents around service boundaries through MCP. The README shows concrete capabilities, setup steps, example workflow calls, a browser dashboard, and support for search, notifications, and planner-backed chat, giving enough evidence for a useful public listing.
The snapshot does not show install/runtime verification, API reference depth, or maintenance signals beyond commits and test count. It is also unclear how the planner layer behaves in practice, what integrations beyond MCP are supported, or how teams would adopt it in an existing codebase.
Last evaluated 7 days ago. Current rank #384. 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.
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.
