mission-control and codesession-cli
About mission-control
builderz-labs/mission-control
Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Built on Next.js 16 with TypeScript, it uses SQLite for persistence and WebSocket/SSE for real-time updates—no external databases required. Supports multi-gateway connections with framework adapters for OpenClaw, CrewAI, LangGraph, and AutoGen, plus a Skills Hub for discovering and auditing agent capabilities from public registries. Features a four-layer security evaluation framework with trust scoring, secret detection, and MCP call auditing across configurable hook profiles (minimal/standard/strict).
About codesession-cli
brian-mwirigi/codesession-cli
Track what your AI agents cost including files, commits, tokens, budgets. CLI , Dashboard+ API. Works with OpenClaw, Claude Code, and any agent framework.
Provides local API interception via an HTTP proxy (listening on localhost only) that captures Anthropic and OpenAI API calls in real-time, storing all metadata in a SQLite database without persisting prompts or keys. Integrates via ClawHub skills, Model Context Protocol, or wraps any script with `cs run`, plus offers a local web dashboard with budget alerts, session timelines, and per-model cost breakdowns—all without cloud dependency or telemetry.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work