3,748 tools found
Benchmark for evaluating LLM agents on fixing real-world CVEs inside sandboxed Docker containers, scored against maintainer tests.
lowfat is a lightweight CLI that filters verbose shell output and file content before it reaches an AI agent, cutting token cost.
Windows companion for OpenClaw: connects a PC to a gateway and gates which Windows capabilities agents can use.
An AI code review CLI, from Alibaba's internal reviewer, tuned for precision over general-purpose coding agents.
vLLM KV-cache quantization backend that gives 3-5x more cache capacity and up to 1.3x throughput over FP16, at FP16-level accuracy.
mnemo is a local Rust sidecar that gives any LLM persistent memory by extracting entities into a SQLite knowledge graph and returning ranked context.
Scan npm packages and lockfiles for supply-chain threat patterns, export findings, and apply severity policies in CI.
Paseo is a self-hosted daemon that runs Claude Code, Codex, Copilot, OpenCode, and Pi coding agents in parallel from desktop, mobile, or CLI.
MCP server, CLI and Python library for searching Google Flights: detailed flight search and cheapest-date search with rich filters.
MCP server for AI image generation across OpenRouter, Together AI, Replicate, and fal.ai.
Publora Skills let an AI agent draft, schedule, and publish posts across 10 social networks through one MCP server instead of ten APIs.
Post and manage content across 10 social platforms - Instagram, LinkedIn, TikTok, X, Telegram, and more - from one AI agent via Publora.
