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

akitaonrails/ai-memory

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors observed · 2026-08-28

github.com/akitaonrails/ai-memory · Rust · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

76/100

  • Activity 99
  • Release rhythm 87
  • Longevity 7

Flags: young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0.0
  • age_days: 104
  • days_rel: 7
  • days_push: 7
  • n_releases_24m: 93

Full methodology

Adoption not part of the score

4845 stars · 345 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A Rust CLI and MCP server that provides long-term memory for AI coding agent CLIs like Claude Code, Codex, and Devin. It captures session context and enables handoff between different agent vendors so work can continue without re-explaining architecture or decisions.

Use cases

  • persist long-term memory across AI coding agent sessions
  • hand off a task from Claude Code to OpenAI Codex mid-project
  • resume coding sessions without re-explaining architecture
  • capture failed approaches and open questions between agent runs
  • inject session handoff summaries at agent startup
  • share context across different AI agent vendors

When to choose

  • you use multiple AI coding agent CLIs and want continuity between them
  • you want automatic session capture and handoff via lifecycle hooks
  • you need an MCP-compatible memory server for coding agents

When to avoid

  • you need memory for chat applications rather than coding agent CLIs
  • you require native Windows support in production (still experimental)
  • you only use a single agent and don't need cross-vendor handoff

Facets

cli-tool · maturity active

mcp agent-framework llm-inference developer-tools cli developer-tools large-language-models windows rust cli ai-coding-agents long-term-memory session-handoff claude-code codex mcp-server ai-agents command-line linux macos docker

1 source

Member repositories

RepositoryRoleHealth v2
akitaonrails/ai-memorymain76

For agents

markdown · JSON · MCP: product_card(name="akitaonrails/ai-memory")

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