OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Contextlattice

Contextlattice is a Go-based, local-first context layer that gives AI agents durable continuity, explainable retrieval, portable context and reviewed learning across harnesses.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Contextlattice — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an agent workflow must preserve mission state beyond a single conversation or move work across harnesses, models, tools or computers.

Who it is for

  • Developers building long-horizon AI-agent workflows
  • Teams that need project context to persist across sessions, models, tools or machines
  • Operators preferring local or self-hosted context management
  • Builders integrating agent memory through CLI, HTTP or MCP surfaces

Documented uses

  • Reconstruct an active objective from durable checkpoints and current state
  • Retrieve compact, high-signal evidence with provenance
  • Carry bounded context between agents and machines
  • Record outcomes and review reusable behaviour before promotion
  • Maintain local agent memory while using explicit, caller-authorized provider execution
Before you choose

Requirements & limits

The repository is public, open source and licensed under Apache-2.0. The documented runtime is local-first and self-hosted rather than a hosted service.

  • The CLI is the primary interface, with HTTP, MCP and dashboard surfaces as companions.
  • Installation uses a Compose v2-compatible container runtime and several command-line utilities.
  • Contextlattice preserves context and evidence but does not replace an agent harness or execute imported context.
  • Agent integration writes bounded managed blocks and does not install third-party harnesses.
  • MCP connection is Likely compatible; the supplied material does not show a concrete integration example or supported harness list.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and verify a local Contextlattice runtime

Prepare the repository, launch the local stack and check the health, state and context-retrieval paths.

Before you start

  • macOS, Linux, or Windows through WSL2
  • A Compose v2-compatible container runtime
  • gmake, jq, rg, python3, curl
  • A Git checkout of the Contextlattice repository

Steps

  1. Clone the repository and change into its directory.

  2. Copy .env.example to .env and run gmake quickstart.

  3. Check the gateway health endpoint with curl and jq.

  4. Run contextlattice doctor --pretty and contextlattice state status --pretty.

  5. Run the documented context command to exercise the retrieval path and inspect its reported coverage, degradation, evidence and next actions.

Expected outcome

A locally launched Contextlattice stack with initial readiness, state inventory and context-path checks performed through the documented CLI and endpoint commands.

Guide limitations

  • The guide documents installation and verification, not a successful agent task execution.
  • The macOS baseline uses OrbStack through its explicit Docker context.
  • Healthy containers alone do not verify the complete retrieval path.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
sheawinkler/ContextLattice · Official homepage title · retained in its source language
How we review sourcesSuggest a correction