Local-first RAG memory for AI agents: hybrid + GraphRAG search, MCP server with OAuth 2.1, plugin for Claude Code / OpenCode / Codex.
This repository also configures its own agents. See what agent-brain tells them →
SpillwaveSolutions/agent-brain
Skill Claude Code
Modern Python coaching covering language foundations through advanced production patterns. Use when asked to "write Python code", "explain Python concepts", "set up a Python project", "configure Poetry or PDM", "write pytest tests", "create a FastAPI endpoint", "run uvicorn server", "configure alembic migrations"…
SpillwaveSolutions/agent-brain
Skill Claude CodeOpenCode
Automates the release process for Agent Brain packages, including version bumping, changelog generation, git tagging, and GitHub release creation.
SpillwaveSolutions/agent-brain
Skill OpenCode
Run end-to-end User Acceptance Tests for Agent Brain features. Builds wheels, installs packages, starts a test server, runs tests, and reports results — all without permission prompts.
SpillwaveSolutions/agent-brain
Skill Codex
Add phase to end of current milestone in roadmap.
SpillwaveSolutions/agent-brain
Skill Codex
Generate tests for a completed phase based on UAT criteria and implementation.
SpillwaveSolutions/agent-brain
Skill Codex
Capture idea or task as todo from current conversation context.
SpillwaveSolutions/agent-brain
Skill Codex
Audit milestone completion against original intent before archiving.
SpillwaveSolutions/agent-brain
Skill Codex
Cross-phase audit of all outstanding UAT and verification items.
SpillwaveSolutions/agent-brain
Skill Codex
Run all remaining phases autonomously — discuss→plan→execute per phase.
SpillwaveSolutions/agent-brain
Skill Codex
List pending todos and select one to work on.
SpillwaveSolutions/agent-brain
Skill Codex
Archive accumulated phase directories from completed milestones.
SpillwaveSolutions/agent-brain
Skill Codex
Archive completed milestone and prepare for next version.
SpillwaveSolutions/agent-brain
Skill Codex
Route freeform text to the right GSD command automatically.
SpillwaveSolutions/agent-brain
Skill Codex
Execute all plans in a phase with wave-based parallelization.
SpillwaveSolutions/agent-brain
Skill Codex
Execute a trivial task inline — no subagents, no planning overhead.
SpillwaveSolutions/agent-brain
Skill Codex
Post-mortem investigation for failed GSD workflows — analyzes git history, artifacts, and state to diagnose what went wrong.
SpillwaveSolutions/agent-brain
Skill Codex
Diagnose planning directory health and optionally repair issues.
SpillwaveSolutions/agent-brain
Skill Codex
Show available GSD commands and usage guide.
SpillwaveSolutions/agent-brain
Skill Codex
Insert urgent work as decimal phase (e.g., 72.1) between existing phases.
SpillwaveSolutions/agent-brain
Skill Codex
Join the GSD Discord community.
SpillwaveSolutions/agent-brain
Skill Codex
Surface the agent's assumptions about a phase approach before planning.
SpillwaveSolutions/agent-brain
Skill Codex
List active GSD workspaces and their status.
SpillwaveSolutions/agent-brain
Skill Codex
Interactive command center for managing multiple phases from one terminal.
SpillwaveSolutions/agent-brain
Skill Codex
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: