README.md
Local-first memory orchestration for AI systems
ContextLattice
Local-first memory orchestration for AI systems with durable writes, multi-sink fanout, retrieval learning loops, and operator-grade controls.
Overview | Architecture | V3 Roadmap | Installation | Integrations | Troubleshooting | Updates
Why Context Lattice
Context Lattice is built for teams running high-volume memory writes where durability and retrieval quality matter more than prompt bloat.
- One ingress contract (
/memory/write) with validated + normalized payloads. - Durable outbox fanout to specialized sinks (Qdrant, Mongo raw, MindsDB, Letta, memory-bank), plus fast retrieval indexes (
topic_rollups,postgres_pgvector) in the staged read lane. - Retrieval orchestration that merges multi-source recall and improves ranking through a learning loop.
- Code-context enrichment + reranking (symbol overlap, file-path proximity, recency) behind env-gated controls.
- Local-first operation with optional cloud BYO for specific sinks.
Architecture Snapshot
|
|
Quickstart
Prerequisites
- Container app requirement: a Compose v2-compatible container runtime is required (
docker compose), such as Docker Desktop, Docker Engine, or another runtime that supports Compose v2 - Supported host environments: macOS, Linux, or Windows (WSL2)
- Host machine sized for selected profile (
litevsfull) with enough CPU, RAM, and disk gmake,jq,rg,python3,curl- Tested baseline: macOS 13+ with Docker Desktop
Distribution Options (Less technical + dev users)
- Less technical macOS users: DMG bootstrap launcher
https://github.com/sheawinkler/ContextLattice/releases/latest/download/ContextLattice-macOS-universal.dmg - Less technical Windows users: MSI bootstrap installer
https://github.com/sheawinkler/ContextLattice/releases/latest/download/ContextLattice-windows-x64.msi - Less technical Linux users: bootstrap tarball
https://github.com/sheawinkler/ContextLattice/releases/latest/download/ContextLattice-linux-bootstrap.tar.gz - Technical/dev users (default): repo clone or main ZIP
- CLI fallback already exists and remains first-class:
gmake quickstart
Release operator note:
gmake dmg-build
# output: dist/ContextLattice-macOS-universal.dmg
gmake msi-build
# output: dist/ContextLattice-windows-x64.msi
gmake linux-bundle-build
# output: dist/ContextLattice-linux-bootstrap.tar.gz
# attach this file to the latest GitHub release
Personal computer requirements + app versions
| App lane | Recommended profile | CPU | RAM | Storage |
|---|---|---|---|---|
Public v3.2.x (current public release v3.2.3) |
Lite | 2-4 vCPU |
4-8 GB |
25-60 GB SSD |
Public v3.2.x (curren |
Configuration
claude_desktop_config.json
{"mcpServers": {"context-lattice": {"command": "docker", "args": ["run", "-i", "--rm", "contextlattice/server"]}}}Try it
→Write the current project context to the memory store for future retrieval.
→Retrieve relevant context from my memory stores regarding the recent task updates.
→Fan out the current task details to all configured memory sinks.
→Query the memory store for recent code-context enrichment related to the current file path.