Skip to main content
AideMemo logoLocal memory for coding agents

AideMemo

Agent-friendly SDK memory for coding agents.

Project memory that survives sessions, editors, and model providers. One Rust binary, one embedded store, and a default local loop that does not require an external LLM call.

Install from sourcecargo install --git https://github.com/taeyun16/aidememo aidememo-cli

Measured, with boundaries

Evidence before adjectives.

Public claims stay attached to a dataset, retrieval stack, and execution envelope.

Read the scorecard
0.992R@10

LongMemEval-S, 500 questions, opt-in BGE plus two-stage rerank

5.7×faster

Daemon BM25 versus fresh CLI, with the same BrainBench score

18.4ms p50

Shared HTTP MCP, two clients and twenty persisted writes

Featured use case

Switch accounts, not context.

Let isolated Codex profiles share project decisions, lessons, and errors without sharing credentials, cookies, or chat history.

See the multi-profile setup
CODEXAccount Aactor: codex:account-a
AIDEMEMOProject memorysource: project:aidememo
CODEXAccount Bactor: codex:account-b

The local memory loop

Memory that stays close to the work.

Capture explicitly, retrieve deliberately, and expose only the context the next task needs.

01Capture

Keep the facts that should outlive this session.

Decisions, lessons, errors, preferences, and relations stay explicit instead of disappearing into a transcript.

aidememo fact add "Use Redis Cluster" \ --type decision --entities Redis,Cache
02Retrieve

Recall the right context before the next plan.

BM25-first search stays fast and deterministic, while semantic retrieval steps in when lexical evidence is weak.

aidememo query "Redis cache" --depth 2
03Apply

Bring memory into the tool already doing the work.

Use the same local store through MCP, the agent SDK, the CLI, or native bindings without adopting a hosted runtime.

aidememo init --agent codex ./wiki

AIDEMEMO / 0.1

Give the next session a better starting point.