Song magic for your codebase.
Persistent memory, multi-repo orchestration, and adversarial quality gates for AI coding agents — across every major IDE. Without changing how you code.
- 9
- Agents
- 49+
- Skills
- 78
- Commands
- 5
- IDEs
The Problem
Your AI agents forget everything the moment you close the chat.
Session 1: You explain your architecture, your constraints, why you chose Postgres over Mongo.
Session 12: The agent uses SQLite. Because it doesn't remember session 1.
You're running 4 repos — api, web, mobile, shared-lib. When something changes in shared-lib, every downstream repo needs to know. There's no mechanism for that.
You ask the same agent that wrote the code to verify it. It passes everything — of course it does. The bugs it introduced are invisible to it.
Galdr is the infrastructure layer that fixes all three. It wraps around your AI IDEs and gives agents durable memory, cross-repo coordination, and adversarial quality enforcement.
What Galdr Gives Your Agents
Four pillars of AI-assisted development
Choose Your Tier
Three tiers, one framework
Start free with Slim. Graduate to Advanced when you need the vault and multi-project orchestration. Add Valhalla when your team needs shared server memory.
| Feature | Slim | Advanced | Valhalla |
|---|---|---|---|
| Task Management | |||
| TASKS.md + tasks/ lifecycle | ✅ Ready | ✅ Ready | ✅ Ready |
| Sequential task IDs + complexity scoring | ✅ Ready | ✅ Ready | ✅ Ready |
| Sprint planning + dependency tracking | ✅ Ready | ✅ Ready | ✅ Ready |
| Adversarial two-phase code review | ✅ Ready | ✅ Ready | ✅ Ready |
| Bug tracking + quality metrics | ✅ Ready | ✅ Ready | ✅ Ready |
| Agents | |||
| 9 specialized agents (task, QA, review, infra…) | ✅ Ready | ✅ Ready | ✅ Ready |
| PCAC coordinator agent | — | ✅ Ready | ✅ Ready |
| IDE Support | |||
| Cursor | ✅ Ready | ✅ Ready | ✅ Ready |
| Claude Code | ✅ Ready | ✅ Ready | ✅ Ready |
| Gemini | ✅ Ready | ✅ Ready | ✅ Ready |
| Codex + OpenCode | ✅ Ready | ✅ Ready | ✅ Ready |
| Memory & Knowledge | |||
| Architectural constraints + learned-facts | ✅ Ready | ✅ Ready | ✅ Ready |
| Obsidian-compatible knowledge vault | — | ✅ Ready | ✅ Ready |
| Platform doc crawling (Cursor, Claude, etc.) | — | ✅ Ready | ✅ Ready |
| YouTube transcript ingestion | — | ✅ Ready | ✅ Ready |
| Semantic cross-session memory search | — | — | ✅ Ready |
| Multi-project (PCAC) | |||
| Parent/child/sibling topology | — | ✅ Ready | ✅ Ready |
| Task broadcast + cascade | — | ✅ Ready | ✅ Ready |
| INBOX cross-project coordination | — | ✅ Ready | ✅ Ready |
| Backend (Valhalla) | |||
| Docker MCP server (42 tools) | — | — | ✅ Ready |
| Oracle DB query/execute | — | — | ✅ Ready |
| MediaWiki integration | — | — | ✅ Ready |
| Video analysis pipeline | — | — | 🔄 In dev |
| Optional Skill Packs | |||
| Infrastructure (K8s, Terraform, CI/CD) | — | ⚡ Enhancing | ⚡ Enhancing |
| AI/ML dev + cloud GPU training | — | ⚡ Enhancing | ⚡ Enhancing |
| Startup tools (VC, formation, product) | — | ⚡ Enhancing | ⚡ Enhancing |
| AI video + 3D graphics | — | ⚡ Enhancing | ⚡ Enhancing |
Changelog
Actively maintained and evolving
Latest releases across all tiers. Scroll each column to see full version history.
Release History
- ›Feature pipeline: staging→specced→committed→shipped lifecycle
- ›g-skl-reverse-spec: 5-pass deep repo analysis
- ›g-skl-harvest-intake: harvest report → feature staging
- ›OpenCode IDE support added (5th IDE target)
- ›12 pre-commit/push hooks including PCAC inbox check
- ›PCAC multi-project coordination system (10 skills)
- ›Parent/child/sibling topology with bidirectional linking
- ›Task broadcast cascade with configurable depth (1-3)
- ›INBOX.md cross-project message routing
- ›g-skl-pcac-spawn: create new project from topology
- ›Initial release — 9 agents, 47 skills, 76 commands
- ›5-IDE parity: Cursor, Claude Code, Gemini, Codex
- ›Adversarial two-phase code review gate
- ›Architectural constraints system (CONSTRAINTS.md)
- ›File-first architecture — zero external dependencies
Release History
- ›Obsidian-compatible vault with YAML frontmatter schema
- ›Shared vault support: multiple projects contribute to one knowledge base
- ›g-skl-harvest: analyze external GitHub repos — zero writes without approval
- ›7 optional skill packs: infrastructure, AI/ML, startup, video, 3D, content, blockchain
- ›All Slim v1.1.0 features
- ›Vault location config in .identity (LOCAL or shared path)
- ›Session summaries auto-captured to vault after each conversation
Release History
- ›Docker Compose stack: Postgres, pgvector, crawl4ai, galdr API
- ›memory_search + memory_capture_session tools
- ›galdr_install MCP tool for remote project initialization
- ›galdr_health_report: per-subsystem project health scores
- ›Initial beta — core memory ingest + search pipeline
- ›Firecrawl profile for platform doc ingestion
- ›get_service_url: environment-aware URL resolution
Release History
- ›Feature pipeline: staging→specced→committed→shipped lifecycle
- ›g-skl-reverse-spec: 5-pass deep repo analysis
- ›g-skl-harvest-intake: harvest report → feature staging
- ›OpenCode IDE support added (5th IDE target)
- ›12 pre-commit/push hooks including PCAC inbox check
- ›PCAC multi-project coordination system (10 skills)
- ›Parent/child/sibling topology with bidirectional linking
- ›Task broadcast cascade with configurable depth (1-3)
- ›INBOX.md cross-project message routing
- ›g-skl-pcac-spawn: create new project from topology
- ›Initial release — 9 agents, 47 skills, 76 commands
- ›5-IDE parity: Cursor, Claude Code, Gemini, Codex
- ›Adversarial two-phase code review gate
- ›Architectural constraints system (CONSTRAINTS.md)
- ›File-first architecture — zero external dependencies
ᚷᚨᛚᛞᚱ
Ready to forge your workflow?
Galdr is open-source and MIT licensed. Install it in any project in minutes — no external services, no subscriptions, no magic until you copy the files.