
from project-orchestrator124
A Rust-based orchestrator that coordinates multiple coding agents using a Neo4j knowledge graph, Meilisearch semantic search, and Tree-sitter parsing to manage
Project Orchestrator sets up a backend that coordinates multiple AI coding agents across projects. It builds a Neo4j knowledge graph of code and decisions, provides Meilisearch-powered semantic code search, and uses Tree-sitter for precise parsing across languages. It exposes APIs and CLIs for syncing code, creating plans, managing tasks, and recording decisions.
Use this skill when multiple agents need shared context for large or complex codebases, when you want structured plans/tasks with dependencies, or when you need persistent recording and search of decisions and code relationships. Useful for multi-agent CI, research projects, or large engineering teams automating development workflows.
Designed for agents that orchestrate other agents or need to integrate with MCP tools (Claude Code, Cursor, OpenAI agents). Also useful for developer-facing assistants that produce or analyze code across languages.
Project Orchestrator coordinates multiple AI coding agents via a Neo4j knowledge graph, Meilisearch, and Tree-sitter. It's a Rust project requiring Docker backends and a separate frontend repo. All 10 scripts failed due to missing dependencies (cargo, docker, backend services). The SKILL.md is comprehensive but monolithic — the entire API reference is inline rather than in references/. Hardcoded default credentials in docs and shell injection risks in plan.sh reduce the security score.
cargodockerneo4jmeilisearchproject-orchestrator-frontendWell-architected project with extensive API surface (22+ endpoints). SKILL.md serves as both docs and agent instructions — could benefit from splitting into references/. The seed scripts for RFC knowledge, protocols, and skills are thoughtful additions for bootstrapping. No malicious intent detected; security issues are standard dev-tooling concerns (default creds, unquoted vars).