LabscoMCP early access ↗
elara-labsMCP SERVER

code context engine

Index a codebase locally so your agent searches it instead of re-reading whole files every session.

by elara-labs ↗Code Intelligence & Repository IndexingCommunity

LABSCO SUMMARY

Cross-session memory and code search from one local index.

The search half is what most indexers give you; the session half is the unusual part - decisions and touched files are recorded as you work and come back on the next run, so context survives a restart. A dashboard and a savings command turn the effect into figures you can check rather than take on faith.

What it is

A local index over your repository - chunks, embeddings and a graph of calls and imports - exposed as MCP tools. Nothing leaves the machine, and one index serves whichever editor you happen to be in.

What you get

  • Hybrid vector and BM25 search over the codebase, expanded along graph edges
  • Full source for any compressed result, pulled back on demand
  • Related code found through call and import edges rather than filename guessing
  • Decisions and worked-in areas recorded now and recalled in a later session
  • A turn-by-turn timeline of a past session, drillable down to the raw input and output of one event
  • Index freshness checks, targeted or full re-indexing, and a switch for how verbose responses are

Requirements

Python 3.11+ and a C compiler for the tree-sitter grammars. One command sets everything up: uvx --from "code-context-engine[local]" cce init, which indexes the project and writes the MCP config for whichever editors it detects. If Ollama is already running it is used for embeddings instead.

Setup effort

One command — uvx --from "code-context-engine[local]" cce init

See installation options