veto

89 agentic tools. 49 specialists. Every major AI CLI. Self-learning. Zero extra cost on subscriptions.

An MCP server that runs locally on your machine, plugs into Claude Code, Codex CLI, Gemini CLI, Antigravity CLI, Cursor, Windsurf, Zed, and JetBrains using your existing subscriptions — giving every AI a council of specialist agents, local LLM support, SDD agents, playwright automation, persistent cross-platform memory, a self-learning router that re-tunes its tier thresholds automatically every 20 recorded task outcomes (reviews record outcomes for you; configurable via auto_apply_learning), CI/CD gates, workspace discovery, and bidirectional IDE communication.

Billing note: "Zero cost" applies to subscription plans (Claude Max, Gemini Advanced, etc.). If you are on API/pay-per-token billing, MCP Sampling calls made by Veto agents will count toward your token usage. veto init detects API key environment variables and warns you automatically.

How the Agents Work

No API keys, zero extra cost. Every worker agent is a deterministic expert module at its core, with two optional layers of LLM reasoning on top — all of it delegated to the AI you're already paying for.

Default — Deterministic expert modules

Out of the box, each of the 42 worker agents runs as a hand-written expert module (plan() / analyze() in src/agents/) — real heuristics like regex/AST secret detection, OWASP/CWE rules, and complexity metrics, not an LLM. They always run, work offline, and cost zero tokens.

Phase 1 — LLM upgrade via MCP Sampling

When a tool is called with llm_backed and your client supports MCP Sampling (server.createMessage), the agent upgrades to real LLM reasoning for a richer plan or analysis. The call runs on your existing subscription — no separate billing.

Phase 2 — Agentic fallback

If Sampling is unavailable, Veto returns an llm_upgrade prompt instead. The host AI reads the specialist's role, reasons itself, and passes the JSON back to complete the operation.

The 7-agent Council is LLM-first — its value is the multi-agent debate — but it too falls back to a deterministic verdict when Sampling is unavailable. When multiple agents run, they execute in parallel.

Specialist Roles

49 specialists: 42 deterministic worker agents across 6 domains + a 7-agent Council. The Council debates trade-offs before you build; the worker agents do the hands-on analysis and planning. Each is a deterministic expert module that can upgrade to LLM reasoning — see How the Agents Work. List them anytime with veto agents.

Council (7) Lead Dev · PM · Architect · UX · Devil's Advocate · Legal · Security

Development (12) Coder · Code Reviewer · Tester · Debugger · Refactor · Database · API · Frontend · Backend · DevOps · Performance · Migration

Security (6) Security Scanner · Auth Agent · Data Privacy · Secrets Agent · Dependency Audit · Penetration Tester

Memory (5) Context Manager · Decision Logger · Project Mapper · Pattern Learner · Knowledge Base

Research (7) Researcher · Tech Advisor · Cost Analyzer · Competitor Analyzer · Risk Assessor · Estimator · Ethics & Bias

Quality (5) Code Quality · Documentation · Accessibility · Compatibility · Error Handling

Workflow (7) Task Planner · Task Coordinator · File Manager · Git Agent · Search Agent · Reporter · Automation

MCP Tools (89)

... View full README on GitHub