Back to directory

one-context

An experimental local background service that watches a project's repositories and compiles their changing state into a compact context artifact an AI assistant can read directly.

one-context

one-context is an experimental local context compiler: a background service that auto-discovers or registers project folders, watches them for Git and file changes, and compresses meaningful changes into a small context artifact that Claude, Codex or another assistant can read directly, aiming for deterministic, always-available project handoffs. The service compiles repository state from Git and file changes rather than reading a model's private conversation context, and an LLM (a local Ollama server or an API) can optionally improve a handoff's language, but never becomes the source of truth.

A single command registers folders, starts the background service, and writes assistant-ready artifacts automatically; a status command reports daemon health, including a machine-readable JSON mode for scripts. File events are debounced with a 15-minute reconciliation scan.

The project describes itself as an alpha research and learning project, not yet a production-ready context-management system, and is written in Go.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.