Ross ROSS = Recommend OSS · open-source software intelligence for agents

Einsia/OpenChronicle

None observed · 2026-08-28

github.com/Einsia/OpenChronicle · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

50/100

  • Activity 81
  • Release rhythm 35
  • Longevity 9

Flags: no_releases young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 134
  • days_rel: n/a
  • days_push: 116
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

2670 stars · 219 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

OpenChronicle is a local-first, open-source memory layer for tool-capable LLM agents, running on macOS. It captures structured context from the accessibility tree (with screenshots as a secondary signal) and turns it into persistent Markdown and SQLite memory that any model-agnostic agent, especially MCP clients, can query.

Use cases

  • give my AI agent persistent memory of what I'm working on
  • open-source alternative to OpenAI Chronicle for agent memory
  • store agent context locally as Markdown instead of the cloud
  • let an MCP client remember my apps, decisions, and projects
  • build a memory layer for tool-using LLM agents with Ollama or LM Studio
  • capture working context from my Mac's accessibility tree for an agent

When to choose

  • you want local-first, inspectable agent memory on macOS with no cloud dependency
  • you need a model-agnostic memory layer that works with any tool-capable agent or MCP client
  • you prefer cheap, structured AX-tree context over screenshot-heavy vision pipelines
  • you want memory stored in readable Markdown and SQLite you can hack on

When to avoid

  • you need Windows or Linux support - it is macOS only
  • you need a production-stable system - it is early alpha (v0.1.0)
  • you rely primarily on visual/screenshot-based context rather than app and text context
  • you need a hosted, multi-device synced memory solution

Facets

application · maturity experimental

agent-framework mcp rag nlp llm-inference database markdown artificial-intelligence large-language-models privacy self-hosted developer-tools python self-hosted agent-memory local-first accessibility-tree screen-context model-agnostic mcp-server openai-chronicle-alternative early-alpha ai-agents macos desktop

1 source

Member repositories

RepositoryRoleHealth v2
Einsia/OpenChroniclemain50

For agents

markdown · JSON · MCP: product_card(name="Einsia/OpenChronicle")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem