← all tools
◆ VECTOR DB RAG
ai-memory
v1.34.0 open-sourceSolution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
ai-memory workstreams --json ai-memory-importer conversation.json --apply
Summary
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Examples
Command line
No option matches that search.
option surface across analysed releases
options at that release added, per release removed, per release
| option | found in | since | description |
|---|
No option matches that search.
option changes per release — drag across the rail to set a range
Values are placeholders taken from each option’s declared default. Nothing is executed here — the output shown is a recording of a run that already happened.
Release history
- v1.34.0
ai-memory v1.34.0 adds a dedicated
EMBEDDING_API_KEY, a generic external-conversation importer with--apply, and theworkstreamssubcommand.└──▷ GET THIS VERSION$ git clone --branch v1.34.0 https://github.com/akitaonrails/ai-memory.git # already have the repo? check out this version: $ git checkout v1.34.0
└──▷ TRY ITList recent managed workstreams for the current checkout in machine-readable form to feed into scripts or dashboards.$ ai-memory workstreams --json
Import an external conversation export into the pipeline, committing it after a dry-run review.$ ai-memory-importer conversation.json --apply
- ›Adds
EMBEDDING_API_KEYenvironment variable as an optional embedding-only credential resolved ahead ofOPENAI_API_KEYandLLM_API_KEY, lettingopenaiandopenai-compatembedding providers use a separate key from the chat model; resolution order foropenaiisEMBEDDING_API_KEY→OPENAI_API_KEY→LLM_API_KEY(last only with a custom base URL), and foropenai-compatisEMBEDDING_API_KEY→LLM_API_KEY. - ›Adds
ai-memory workstreamssubcommand for a read-only checkout-local list of recent managed workstreams with the current selection first, linked harnesses, timestamps, and stable ids; supports human-readable and--jsonoutput. - ›The
ai-memory-importercompanion can now replay bounded generic external-conversation JSON into the observation/consolidation pipeline; dry-run by default,--applysends one ordered/hook/batchwith theexternal-importwire identity, with stable session/event idempotency keys, event/byte caps, and a durable partial-failure manifest for safe resumption of interrupted imports.
- ›Adds
- v1.33.0
Session pages now expose originating agent as
agentfrontmatter, surviving LLM rewrites and compaction checkpoints.└──▷ GET THIS VERSION$ git clone --branch v1.33.0 https://github.com/akitaonrails/ai-memory.git # already have the repo? check out this version: $ git checkout v1.33.0
- ›Generated
sessions/<id>.mdpages now include anagentfrontmatter field alongsidesession_id, recording the originating harness so that LLM rewrites, compaction checkpoints, spool drains, and superseding versions cannot overwrite the origin attribution; manual page writes remain unattributed.
- ›Generated