# openTrinity/mycontext

MyContext is a local-first desktop app for everyday communication and knowledge work

Repository: https://github.com/openTrinity/mycontext
Canonical: https://ross.abutalabs.com/products/mycontext
Homepage: https://mycontext.md
Language: TypeScript
License: NOASSERTION
License Family: other
Last push: 2026-08-17T07:47:21+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 35, longevity 2
- inputs: {"age_days": 30, "days_push": 16, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1998, forks 133 (observed 2026-08-28T04:05:58.239504+00:00)

## What it is
MyContext is a local-first desktop application that builds a persistent personal work context layer by connecting signals from instant messaging, documents, calendars, meetings, and local activity into a private, evolving context graph. It enables large language models, local agents, and authorized AI applications to retrieve from and reason over this personal context, with features like a digital self for handling work conversations and natural-language search with traceable source material.

## Use cases
- search my work history across messages and documents in natural language
- build a personal knowledge graph from my conversations and meetings
- let AI draft replies to work messages in my own style
- connect scattered work context from IM, calendars, and docs into one place
- give local AI agents access to my personal work context
- find past project decisions and shared notes quickly
- keep a private, on-device record of who I work with and what I'm working on
- track follow-ups and things that still need attention from my communications

## When to choose
- you want a private, local-first AI workspace that keeps your personal context on your own device
- you need to unify scattered work signals (IM, docs, calendars, meetings) into a searchable knowledge base
- you want AI assistants that reason over your actual work history instead of starting from empty prompts
- you prefer explicit approval gates before any AI takes consequential actions on your behalf
- you want to choose your own models and gateways for AI assistance

## When to avoid
- you need a stable, production-ready tool — it's in developer preview with breaking changes expected
- you can't tolerate database migrations that may require re-running collection or losing non-reversible changes
- you want a cloud-synced solution accessible from multiple devices
- you need team-wide or organizational knowledge sharing rather than individual personal context
- you're unwilling to act as an early tester for rapidly iterating software

## Facets
- artifact type: application
- maturity: experimental
- function: search-engine, rag, llm-inference, agent-framework, chatbot, nlp, database, self-hosted
- domain: artificial-intelligence, large-language-models, developer-tools, privacy, self-hosted
- platform: cross-platform
- tags: personal-context-graph, local-first, digital-self, sqlite-vault, semantic-search, knowledge-work, ai-workspace, developer-preview, retrieval-augmented-generation, ai-agents, knowledge-management, desktop, local

## Member repositories
- openTrinity/mycontext (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:58.239504+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:02:14.221417+00:00, confidence not recorded.
  - readme: https://github.com/openTrinity/mycontext (fetched 2026-08-28T04:05:58.239504+00:00, sha 8125e2ac2624)
  - homepage: https://mycontext.md (fetched 2026-08-29T10:42:17.732155+00:00, sha 0d5dab5f46e4)
- Data as of 2026-08-30T08:39:29.467469+00:00.