Runtime Firewall for AI agents which catches the rogue tool call before it runs. Dangerous commands, secret leaks, prompt injection. For Claude Code, Codex and framework SDKs

duck.ai openai compatible api server

Local OpenAI-compatible proxy for Qoder CN CLI, for learning only

OpenAI Codex CLI session log viewer for JSONL files in ~/.codex/sessions. Browse conversations, tool calls, tokens, collaboration chains, and live sessions on desktop and web.

Local monitor for Claude Code API traffic, logs, prompts, and tools

🦞 Web UI for browsing OpenClaw session tool call history. Zero dependencies, just Node.js.

The governance layer for AI agents — monitor reasoning, audit tool calls, and secure the loop through OHTTP privacy routing.

A micro-CLI to apply tool calls from Anthropic for their text_editor_20250124 built-in computer use tool

Connect, setup, secure and seamlessly manage LLM models using an Universal/OpenAI compatible API

Open source action governance SDK for AI agent tool calls.

Multiplexer for MCP tool calls: parallel execution, batching, caching, and pipelining for any MCP server

Local PII and secret redaction for Python LLM apps and AI agents. Zero dependencies. Prompts, tool calls, MCP, memory, logs, and traces.

Runtime approval gates for AI agent tool calls. Intercept payments and emails before execution

Decode, reconstruct & validate captured OpenAI / Anthropic streaming (SSE) responses. Zero deps, CLI + library.

Turn an LLM agent conversation (OpenAI or Anthropic JSON) into a Mermaid sequence diagram, Markdown timeline, or plain-text trace. Zero deps.

One line to instrument your agent and capture every event in an immutable, queryable audit trail.

RunWhy: local flight recorder and time diagnosis for AI coding agents.

Debug and inspect OpenCode sessions with timelines, analytics, and tool insights.