Waystone · by Unbidden AI
Persistent memory for AI-assisted development. Works with any OpenAI-compatible model via MCP or REST API.
# Query your project memory
waystone query my-project "what auth approach did we decide on?"
→ Auth: JWT, stateless, multi-region. Decided 2026-03-01.
→ Database: PostgreSQL via Supabase. Rejected SQLite.
The problem
Waystone was built specifically for each of these. Not workarounds — architectural fixes.
Your 4K context fills up at turn 15. Every session starts with re-explaining what you built two days ago. Waystone extends it to unlimited — relevant facts only, no noise.
You're paying for every token in history. Stuffing prior context into every call is expensive. Waystone cuts that by 60–80% by sending only what matters for the current task.
Week 6 AI contradicts week 1 decisions. You've said "we're using PostgreSQL" six times. Waystone makes that decision permanent — retrieves in week 12 the same as week 1.
How it works
A graph-based knowledge store with semantic retrieval and temporal decay scoring.
One config block in Claude Code, Cursor, Windsurf, or Continue.dev. The MCP server runs as a background process — zero impact on your editor.
At session end, waystone_extract processes your conversation. Decisions, constraints, implementation details, and open questions are extracted and merged into a persistent knowledge graph.
waystone_query returns the facts most relevant to your current task. Superseded facts retire automatically — old decisions don't clutter the context.
Integrations
If it speaks MCP or HTTP, it works with Waystone.
Claude Code — ~/.claude/settings.json
{
"mcpServers": {
"waystone": {
"command": "waystone",
"args": ["mcp-serve"],
"env": {
"WAYSTONE_PROJECT": "my-project"
}
}
}
}OpenClaw — openclaw.json
{
"mcpServers": {
"waystone": {
"command": "waystone",
"args": ["mcp-serve"],
"env": {
"WAYSTONE_PROJECT": "my-project"
}
}
}
}See the full integration guide for Cursor, Windsurf, Continue.dev, Cline, and Zed — with exact config file paths for each tool. Using Hermes? See the Hermes MemoryProvider guide →
Get started
Waystone is in active development. Sign up and we'll reach out when the CLI is ready for your setup.
Early access includes the full CLI, MCP server, and hosted sync. Free tier available at launch — no credit card required to sign up.
FAQ
RAG retrieves from a document corpus — you put documents in, it fetches chunks when asked. Waystone builds memory from conversations — it watches what you're working on, extracts decisions and facts as you go, and surfaces them in future sessions automatically. It's session memory, not document search.
Built-in memory tools summarize old context or drop it when the context window fills. Architectural decisions from early in a project eventually disappear. Waystone extracts structured facts — it doesn't summarize or discard. A decision from week 1 retrieves just as accurately in week 12 as it did on day 2.
Local mode: Nothing leaves your machine. The MCP server runs locally, extraction calls your configured LLM endpoint, and the memory store is a local file. Hosted mode: Session text is sent to the Waystone API for extraction. Your data is always exportable via waystone export.
Yes. Waystone works with any OpenAI-compatible endpoint. Gemini Flash is the recommended extraction model for cost and accuracy — local extraction via Ollama is supported and documented.
When a new decision supersedes an old one, Waystone marks the old fact as retired. It stops appearing in retrieval. You see the current state of the project — not a history of every decision including ones you've reversed.
95% recall on our benchmark across 23 questions spanning three synthetic projects (API design, auth system, data pipeline). Accuracy is higher with the --verify flag. Full methodology in the repo under benchmarks/.
Gemini Flash costs ~$0.15/1M tokens. A typical 50-turn session generates ~5,000 tokens of transcript. Extraction cost per session: ~$0.001. For a 5-person team at 440 sessions/month: under $0.50/month in LLM extraction costs.