critic-orchestrator is an MCP server that coordinates multiple adversarial AI reviewers in parallel using Claude CLI or any OpenAI/Anthropic compatible API. It acts as an anti-confabulation layer for AI coding agents by rigorously verifying claims and proposed fixes. The open-source tool improves reliability of autonomous coding systems through structured critique.
critic-orchestrator is a LLM eval & observability product. AI coding agents producing incorrect or hallucinated code without sufficient verification. critic-orchestrator is an open-source project aimed at AI developers. The project is open source (MIT). It runs on the command line and API.
Behind critic-orchestrator is aureliocpr-ctrl, and the product first shipped in 2026. The project is developed in the open on GitHub with 45 commits in the last 90 days. Among its 4 catalogued features are adversarial review, parallel verification, and anti-confabulation. It exposes integrations via an MCP server and a public API.
Latest indexed changes and source events
critic-orchestrator verified by the PulseGate indexer
Other apps tracked under the same category.
