liminis-context-graph

A local-first context graph engine. One Rust binary that turns a stream of text into a queryable graph of entities, relationships, and episodes — combining property-graph storage, HNSW vector search, and full-text search in a single embedded service, built on LadybugDB. No database server, no separate vector store, no search cluster: everything runs in one process, on your machine, against files in your workspace.

This page documents v0.16.4, built directly from that release tag’s docs/ tree — not from main. Unreleased changes merged to main since this tag are not reflected here; use the version switcher in the footer to browse other published releases.

Source: github.com/verveguy/liminis-context-graph. The README has a short overview and a standalone quickstart; this site is the full reference.

How it fits together

One process, one socket, one database directory. A client speaks JSON-RPC (or MCP) over a Unix socket; extraction calls out to an LLM; everything else — graph storage, vector index, full-text search, the write-ahead log — is embedded.

Everything inside that boundary is one binary and files in a directory you own. The only arrow leaving it is the LLM call, and a local model keeps even that on your machine.

Multi-graph, not multi-tenant. One process can hold many graphs, each with its own group_id and its own WAL stream — see IPC & MCP Reference: group_ids semantics and Operations for the mechanics. That’s a data-organisation capability for one user’s own workspaces and subscriptions, not tenancy: there is no authentication, no authorisation, and no per-tenant resource isolation. Anything that can reach the socket can reach every group in the database — treat the process boundary as the trust boundary.

Reference pages

• Getting Started — install, run, build from source, bundle in downstream apps.
• Configuration — every environment variable and CLI flag.
• Embedding Options — one capability matrix of local and remote embedding backends: platform, install, cost, and dimension.
• IPC & MCP Reference — the JSON-RPC and Model Context Protocol method surface.
• Telemetry — structured JSONL events emitted on stderr.
• Ontology — the optional entity/relation type vocabulary.
• Operations — WAL administration, degraded mode, and self-healing recovery.
• Testing & Evaluation — LLM cassettes and the extraction-quality eval harness.
• Extraction-Quality Evaluation — evaluation methodology, model rankings, and local-LLM guidance.
• Full-Corpus Extraction Benchmark Runbook — maintainer procedure for full-corpus model comparison.
• Release Process — maintainer procedure for verifying CI status before cutting a release.
• ADR Index — architecture decision records (historical, not current-state, documentation — see the index for framing).

llms.txt

llms.txt and llms-full.txt provide this site’s content in a form suited to LLM ingestion. CLAUDE.md (agent guidance for contributors working in this repository) is referenced from llms.txt but is not itself published here.