Developer Tool / Security / Monitoring
Linux-only kernel-level audit feed for Claude Code or other matched agent sessions, streaming exec, file, and network activity in real time.
The page clearly presents a real AI-adjacent developer tool with a specific job: live auditing of agent sessions from the kernel. The README explains what it tracks, why a normal trace is insufficient, how it works at a high level, and includes quick-start commands and example output, giving enough evidence for a useful public listing.
The snapshot does not show licensing, release/version status, or how mature the project is beyond the repository and README. It also does not show broader platform support beyond Linux or whether the matching/auditing works with agents other than Claude Code in practice.
Last evaluated 10 days ago. Current rank #71. 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.
