Start here
Memory & Intelligence Layer · v7.5.0 · Local-First · Free to Use
Your AI Forgets Everything. Wyrm Remembers, and Learns From Failure.
The local-first memory and intelligence layer for AI agents. It gives Claude, Cursor and Copilot persistent memory across every session, plus a benchmarked firewall that blocks a known mistake before it repeats. Nothing leaves your machine. Free to use.
100% / 100% recall / precision firewall·Local-first · nothing egresses·Measured, not claimed
Or install the CLI: npm install -g wyrm-mcp
New here? 5-minute Getting Started · Questions or ideas? GitHub Discussions
Works with
Claude Desktop·GitHub Copilot·Cursor·Windsurf·Any MCP Client
Ghost Protocol is a member of the NVIDIA Inception program
Pricing
Free Forever. Scale When Ready.
Local use is free with no limits. Paid plans add cloud sync, encryption, and team collaboration.
Free
For individual developers
- Local SQLite storage
- All 150+ tools · 32-verb surface
- Fleet memory + negative learning
- Live Memory + hybrid recall
- Cross-project memory
- Full-text + semantic search
- Unlimited projects
- Community support
Free
Most Popular
Pro
For power users
- Everything in Free
- Cloud sync across devices
- AES-256 encryption
- Priority support
- Advanced analytics
$29
/month
Team
For development teams
- Everything in Pro
- Shared team memory
- Up to 25 seats
- Admin dashboard
- Slack integration
$199
/month
Enterprise
For organizations
- Everything in Team
- Unlimited seats
- SSO / SAML
- Custom SLA
- Dedicated support
- On-premise option
$499
/month
Need a custom plan? Contact us →
The Problem
AI Has Amnesia
Context window limits mean your AI starts fresh every session. You re-explain your codebase, preferences, and decisions over and over. The workarounds (copy-paste, prompt files, manual context) are all fragile.
The Solution
Wyrm Gives Your AI a Permanent Brain
Wyrm is a Model Context Protocol (MCP) server: the memory and intelligence layer that gives AI agents persistent, searchable memory. Projects, sessions, quests, skills, and arbitrary data, indexed with hybrid full-text and semantic recall and available across every conversation. Local-first and private. Your memory stays on your machine, built on the Wyrm Memory Protocol. Free tier (account required). See how Wyrm compares to other AI-memory tools or read the docs.
Projects & sessions that persist forever
Hybrid recall: full-text fused with semantic vectors
32-verb typed surface: 150+ tools, all callable
Knowledge graph with entity relationships
Ground truths & scaffolds for every context build
Unified capture: one tool classifies anything
Session prime: full context in one call
Run-attributed fleet memory (agent_id, run_id)
Fleet negative learning: one failure blocks it for all
Benchmarked firewall: 100% recall / 100% precision
Portable skills synced across every machine
wyrm render: memory into CLAUDE.md at zero MCP tokens
Install
$ npm install -g wyrm-mcpclaude_desktop_config.json
{
"mcpServers": {
"wyrm": {
"command": "wyrm-mcp"
}
}
}Up and running in under 60 seconds. Full setup guide →
Features
Everything Your AI Needs to Remember
A frozen 32-verb typed surface over 150+ tools: run-attributed fleet memory, fleet negative learning, hybrid recall (with optional NVIDIA NIM embeddings and reranking), the knowledge graph, Live Memory replication, and the render target. The load-bearing nine are below; the full surface is in the docs.
Persistent Memory
Projects, sessions, quests, skills, ground truths: everything kept across every session, local-first.
Hybrid Recall
Full-text (FTS5) fused with semantic vectors and an optional cross-encoder rerank. Local nomic by default; opt into NVIDIA NIM embeddings + reranker for a sharp recall lift, nothing egresses unless you say so.
Benchmarked Firewall
Negative learning, measured: 100% recall / 100% precision blocking a repeated mistake, ~0.1 ms, deterministic. The benchmark ships in the repo.
Fleet Memory
Every write is attributed to the (agent_id, run_id) that produced it, so a swarm of agents shares one accountable memory bus.
Fleet Negative Learning
A failure recorded by one agent blocks the repeat for every sibling, enforced by the wyrm-guard hook before the doomed call runs.
Knowledge Graph
Entity/relationship graph with neighborhood traversal, path finding, and merge. Memory with structure, not just search.
Frozen 32-Verb Surface
A stable, typed verb surface (structuredContent + annotations) an orchestrator can pre-check. 32 advertised verbs; 150+ tools all callable.
Portable Skills
SKILL.md content syncs end-to-end across every machine. Teach a skill once; the whole fleet inherits it.
Render Target
wyrm render compiles your memory straight into CLAUDE.md, AGENTS.md, Cursor and Copilot slots: byte-stable, budget-capped. Casual sessions cost zero MCP tokens.
Stop Losing Context. Start Remembering.
Give your AI the memory it deserves. Free to use, local-first, and ready in 60 seconds.
Built by Ghost Protocol, the studio that ships security tools that actually work.
Changelog
v7.5.0Latest
NVIDIA NIM retrieval
Optional NVIDIA NIM embeddings + reranker as an explicit opt-in beside the local default. On LoCoMo, NIM embeddings lift recall@1 33% → 47% and the reranker again to 52%; nothing egresses unless you turn it on, and the per-recall receipt names any remote scorer that saw text.
v7.4.0
Audit alignment
The claims become the code: truth auto-cascade on supersede, the daemon can act under the same safety whitelist, and enforcement transparency (a blocked verdict names whether the firewall is hard-blocking or advisory on this machine).
v7.0.0
BROOD, fleet memory
Every memory attributed to the (agent_id, run_id) that produced it, so a swarm of agents shares one accountable memory bus. Fleet negative learning, and a frozen 32-verb typed surface over 150+ callable tools.