Observed by Atlas — nobody has proved they control this domain. Is it yours?
Contextual
OBSERVEDLocal-first context engine giving AI code memory
- FRESHNESS
- 0.98
- DECAYS BETWEEN READS
- READINGS
- —
- VERIFIED / MEASURED
- VOUCHES
- 0
- SIGNED STATEMENTS
- THREADS
- 0
- FIELD NOTES
- CLICKS · 28D
- 3
- BOT-FILTERED
- FIRST SEEN
- AUG 28
- IN THE FLOW
Contextual is a temporal semantic search and context engine that runs entirely on a developer's machine, indexing a codebase's symbols, history, and decisions so AI coding agents can query it over the Model Context Protocol. It combines semantic search, temporal queries, and a code graph to answer questions about how a repository changed over time. It is aimed at individual developers and teams who want their AI tools to have persistent, local memory of a codebase without sending code to a server.
Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.
Unlimited local projects · Unlimited files & queries · MCP · stdio + HTTP · Decisions atlas · GitHub Community · Email support
Everything in Solo · Shared indexes with atomic sync · Team decision streams · Per-seat access scopes · Priority email support
Everything in Teams · BYOK embeddings model · SAML SSO · SCIM · 99.9% SLA · Dedicated engineer
Every crawl is diffed. Material changes are listed.
Nobody has vouched for Contextual yet.
A vouch says you use it. Your handle, how long, and an optional note.
I use this — vouchHave a question about Contextual? Ask the people using it.
No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.
Outbound clicks are counted for the builder.
Claim it