This is not another autonomous coder — the agents stay where they are and keep doing the engineering. What it adds is the part that is missing when several of them work on the same repository: one admission point, a voter panel that argues about a change before it lands, an audit log whose integrity is verifiable, and routing that shifts based on what worked last time.
A control plane for the coding agents you already run — Claude Code, Codex, Gemini and OpenCode. It admits work through one entry point, picks a strategy, reviews output with a panel of voters before it ships, and records every tool call and decision in an append-only hash-chained log. 47 tools, package nexus-agents.
- `run` — the default entry point: give it a goal and it returns the routing decision, or executes the strategy inline when you ask it to
- Adversarial pull-request review with 5 voter roles (architect, security, devex, catfish, scope steward) behind a 4-point verification gate — `pr_review`
- Consensus voting on a proposal across a 7-role panel with six named strategies, from simple majority to proof-of-learning — `consensus_vote`
- A quality gate that runs typecheck, lint, tests, build and security over a project directory and returns a structured verdict — `run_quality_gate`
- An audit chain you can check rather than trust: `verify_audit_chain` verifies the hash chain of an audit log directory (tamper-evident, not tamper-proof)
- Codebase intelligence — `extract_symbols` for one file's AST symbols, `search_codebase` for declarations, `search_usages` for the call sites that answer 'where is this used'
- Orchestration across 12 built-in expert roles: `orchestrate`, `create_expert`, `execute_expert`, `run_workflow`, and `run_graph_workflow` for DAGs with per-node checkpoints
- A research system over 9 discovery sources — `research_discover`, `research_analyze`, `research_synthesize`, `research_query`
- Long-running work handled asynchronously: `list_jobs`, `get_job_result`, `cancel_job`, with `query_trace` and `query_task_state` for observability
- Memory that outlives the session and feeds routing — `memory_write`, `memory_query`, `memory_stats`
Node.js 22.x LTS and the npm package nexus-agents installed globally, or the Claude Code plugin. `nexus-agents setup` writes the MCP registration and project rules for up to seven places — Claude, Cursor, OpenCode, Gemini, Codex configs and a project config file — each skippable with its own flag, and `nexus-agents doctor` prints a read-only health table first. Model credentials are per-provider and optional: `ANTHROPIC_API_KEY`, `OPENAI_API_KEY` and `GOOGLE_AI_API_KEY` are read if present, and voting runs through whichever local CLIs you already have without any of them. In MCP mode the server speaks stdio only, with no network exposure; the REST API is opt-in and generates its own key. `NEXUS_TUNE_ENFORCE` turns off the bounded self-tuning loop that demotes unhealthy CLIs.
One command plus a key — npm install -g nexus-agents, then supply credentials