Agent Memory Os

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/yamantaka520-agent-memory-os

About

Use cases: agent-memory

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools

4 read · 7 write · 0 delete · 2 not yet classified

Secrets

None asked for

Install scripts

None found

Runs as

Python package

Tools (13)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• memory_add

  Store a durable memory that will survive across sessions. Use this to remember a user preference, project fact, decision, procedure, or lesson worth recalling later — not transient chat. Set `share` to make it visible to teammates ('team'/'project') instead of just yourself; the default is private. Content is de-duplicated softly and becomes searchable immediately. Returns the new memory's `id`, `content`, and resolved `visibility`, or an `{"error": ...}` object if `share` names a team/project you can't resolve.

• memory_consolidate

  Merge duplicate memories and synthesize concept memories (housekeeping). A periodic hygiene pass: it collapses exact/near duplicates and combines strongly co-recalled clusters into higher-level concept memories, keeping the store compact and recall sharp. Safe to run occasionally rather than per-write. Returns counts of what was merged and created.

• memory_context_pack

  Build a prompt-ready, token-budgeted block of the most relevant memories. Prefer this over `memory_search` when you want text to paste straight into a prompt: it selects and formats the highest-value memories within `max_tokens`, de-duplicates, and flags contradictions. Access-controlled to this agent's identity. Returns a formatted string (empty if nothing relevant is visible).

• memory_link

  Create a directed association between two existing memories. Linked memories reinforce each other in recall, so a search that hits one can surface the other even with no shared keywords. Use it to connect a decision to its cause, or a fix to the problem it solved. Returns the created link, or an `{"error": ...}` object if either memory id does not exist or, when an identity is configured, is not owned by that agent.

• memory_offload_context

  Park the agent's working context as a restorable snapshot (offload). Use before context runs out or when switching tasks, so the work can be reloaded later with `memory_reload_context` instead of being lost. Snapshots are rotated per session. Returns the new `snapshot_id` and `session_id`.

• memory_orchestrate_context

  Assemble a rich, budget-aware context block for a task. A higher-level alternative to `memory_context_pack`: it splits the budget into sections — bedrock constants, proactive warnings and procedures, and relevance recall — in one prompt-ready block. With a `session_id`, repeated calls omit memories already delivered (bedrock constants always repeat). Access-controlled to this agent. Returns `text`, `sections`, `used_tokens`, `max_tokens`, `emphasis`.

• memory_recall_feedback

  Report whether recalled memories were helpful, to tune future ranking. This closes the learning loop: `helpful=True` strengthens the memories and the links between them (they will resurface more readily); `helpful=False` weakens them and lowers their confidence. With a configured identity, only memories owned by that agent are affected; sharing grants recall access, not mutation authority. Returns a summary of what was reinforced or weakened.

• memory_reload_context

  Restore a previously offloaded working-context snapshot (reload). The counterpart to `memory_offload_context`: rehydrates the parked context so the agent can resume where it left off. Returns the snapshot's stored data, or an `{"error": ...}` object if the session/snapshot is not found.

• memory_search

  Recall memories relevant to a query, ranked best-first. Call this before answering to retrieve what you already know. Results are access-controlled: only memories this agent (AGENT_MEMORY_AGENT_ID) is allowed to see are returned — private, its own, its teams'/projects', and global. Each result has `id`, `score` (relevance), `content`, `scope`, and `type`. Returns an empty list if nothing relevant is visible. `since`/`until` narrow the candidates to a time window before ranking, which is how you answer "what did I learn last week" — recency alone only reorders what a query already matched.

• memory_share

  Change who can read an existing memory (share it, or make it private again). Use this to promote a note you already stored to your team/project so collaborators can recall it, or to lock it back down. Only the memory's OWNER may change its visibility. The change propagates over sync — sharing reaches teammates, and making it private retracts it. Returns the memory's `id` and new `visibility`, or an `{"error": ...}` object if it doesn't exist, isn't yours, or `share` is invalid.

• memory_snapshot_diff

  Show what changed between a session's two most recent context snapshots. Answers "what did I change since I last parked this work?" — returns the top-level keys added, removed, and changed between the previous and latest snapshot, or an `{"error": ...}` object if the session has fewer than two.

• memory_timeline

  Recall what was recorded around a moment in time. Explicit links capture associations someone asserted; this surfaces the ones that simply happened together. Debugging sessions, incidents and decisions arrive in bursts, so anchoring on a memory recovers the context around it that no link records. Give exactly one of `anchor_id` or `around`. Results are access-controlled the same way as search, and each carries `offset_seconds` (negative = before the centre, positive = after) so you can reconstruct the order of events. An anchor this agent cannot see returns an empty list.

• memory_update

  Update fields of an existing memory in place (keeps the same id). Use it to correct content, re-weight importance/confidence, or pin a memory so it is never forgotten. Only the fields you pass are changed. Returns the updated `id`, `content`, and `updated_at`, or an `{"error": ...}` object if the id does not exist or, when an identity is configured, is not owned by that agent.

Compare and alternatives

Featured in

• Best MCP servers for multi-agent orchestration

Signals

Stars

7

Forks

2

Open issues

1

Weekly downloads

236

Last commit

Oct 1, 2026 (27 days ago)

Last release

Sep 22, 2026 (1 month ago)

Last package publish

Sep 22, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.yamantaka520/agent-memory-os

Version

1.10.1

Auth

No auth

Packages

pypi agent-memory-os

License

Apache-2.0

Repository

github.com/yamantaka520/Agent-Memory-OS

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql