Type `ralph "prompt"` to start open code in a ralph loop. Also supports a prompt file & status check. Open Code, Claude Code, Codex, Copilot

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.

See how you really use AI — X-ray your AI coding sessions locally

AgnosticUI Local (v2) is a CLI-based UI component library that copies components directly into your project. Works with AI tools, agent-driven UIs, and prompt-ready workflows.

Agent Package Manager

Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

Scan any agent skill — authored or compiled — for prompt injection, secrets, and malicious execution before it touches your agent. Or compile the long tail on the fly.

Open-source observability & evaluation platform for AI agents and coding agents. Trace LLMs, tools, prompts, costs & agent workflows with OpenTelemetry.

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

Local-first AI token usage & cost tracker for 31 coding tools incl. Claude Code, Codex, Cursor, Gemini & DeepSeek Harness—with native apps. Never reads prompts.

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

Self-hosted & federated platform for AI IDE/Tools Rules and Commands via WebUI & CLI - Generate, browse, store, share AGENTS.md, CLAUDE.md, and more

Security scanner for AI agents, MCP servers and agent skills.

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Open-source adversary emulation for AI agents and MCP servers.

Tamper-evident integrity monitor for the MCP config & server files your local AI agents load.

AI-writing humanizer for KO/EN/ZH/JA

Private Skill distribution platform for AI coding agents: publish, install, update, and rollback team skills across Cursor, Claude Code, Codex, and OpenClaw with a minimal server + skb CLI.

Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.

The security-first skill manager for AI agents — every install runs a security scan. Manage skills & MCP servers across 87 agents. Zero-dependency CLI.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.