Pituitary

Created By
autholykos2 months ago
Catch spec drift before it catches you. Pituitary indexes your specs, docs, and decision records, then detects overlap, contradictions, stale docs, and code that drifts from what was decided. 6 tools for spec-aware AI workflows: - search_specs: semantic search across indexed spec sections - check_overlap: detect specs that cover overlapping ground - compare_specs: side-by-side tradeoff analysis of two specs - analyze_impact: trace which specs, docs, and code paths are affected when a spec changes - check_doc_drift: find docs that contradict accepted specs - review_spec: full composite review (overlap + comparison + impact + drift + remediation) Single Go binary. One SQLite file. No API keys required. Deterministic by default.
Overview

What it does

Point Pituitary at your repo. It indexes your specs, docs, and decision records, then catches what you can't track by hand. What you wrote down should still be true. Pituitary makes sure it is.

Tools

ToolDescription
search_specsSemantic search across indexed spec sections. Filter by domain and status.
check_overlapDetect specs that cover overlapping ground. Returns similarity scores and relationship classification.
compare_specsSide-by-side tradeoff analysis of two specs.
analyze_impactTrace which specs, code refs, and docs are affected when a spec changes.
check_doc_driftFind docs that have gone stale relative to accepted specs, with cited evidence.
review_specFull composite review: overlap + comparison + impact + drift + remediation.

Requirements

  • Pituitary binary on PATH (download from GitHub Releases)
  • A config file (generate one with pituitary init --path .)
  • A built index (pituitary index --rebuild)

No API keys required in deterministic mode.

Use cases

  • PR review: Agent calls check_overlap and analyze_impact when a PR touches specs or decision records
  • Pre-merge drift check: Agent calls check_doc_drift to surface stale docs before merging
  • Decision authoring: Agent calls review_spec to get a full assessment of a new or changed spec
  • Impact questions: "What specs and docs would be affected if I change the auth middleware?" triggers analyze_impact

Server Config

{
  "mcpServers": {
    "pituitary": {
      "command": "pituitary",
      "args": [
        "serve",
        "--config",
        ".pituitary/pituitary.toml"
      ]
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
autholykos
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago