Memory
The memory OS for coding agents.
Every pattern learned, every pitfall avoided, every decision made — persisted across sessions, recalled when relevant.
Brain Time Machine and Teams are unlocked on cloud — free during early access.
Free cloud workspaces include 10,000 memories and 1,000 API calls/day, so you can start local and unlock snapshots, shared context, and collaboration when you are ready.
Your agent explained your codebase yesterday. Tomorrow it still knows.
Every pattern, every pitfall, every architecture decision — stored once, recalled across sessions. Your agent loads only what it needs per task (~400 tokens for 3 results) instead of stuffing everything into a system prompt (5,000+ tokens). Less wasted context on every message.
You never have to say "remember this."
Wrap your LLM call with brain.chat() and memory happens invisibly. Before the agent responds, relevant memories are recalled and injected into context. After it responds, new learnings are extracted and stored. Your agent gets smarter with every conversation without you doing anything.
Four strategies. One answer.
Every recall query runs four search strategies simultaneously: alias matching, tag intersection, keyword scoring, and vector similarity. Reciprocal Rank Fusion merges the results into one ranked list. Optionally, a cross-encoder reranker (Pro+, Voyage AI) filters noise. Query expansion catches what you meant, not just what you typed.
Overnight, the brain reorganizes itself.
Inspired by how biological memory works during sleep. Overnight, AgentBay reviews the day's memories: promotes frequently-used knowledge to long-term storage, merges duplicates into concise summaries, surfaces contradictions, and generates topic-level overviews. Your agent wakes up with a cleaner, sharper brain than when it went to sleep.
Wrong memories fix themselves.
When two memories contradict each other, AgentBay doesn't just flag it — it resolves it. The system examines both entries, considers which has been verified more often, which was accessed more recently, and which source is more trusted. The winner stays. The loser fades. No manual cleanup needed.
The brain builds its own map.
As memories accumulate, AgentBay automatically extracts entities — functions, services, APIs, patterns — and links them into a knowledge graph. When your agent recalls one memory, it traverses the connections to find related context: what depends on this service, which patterns relate to this function, what pitfalls surround this API. Graph-augmented recall means deeper, more connected answers.
Remember every user. Personally.
Scope memories by user ID. Thomas prefers TypeScript and dark mode. Sarah works on the API team and needs deployment details. Each user gets their own memory space within your agent. Build chatbots, support agents, and personal assistants that remember who they're talking to — across sessions, across devices.
Something went wrong? Go back.
Before every major operation, AgentBay snapshots the entire brain state. If a bad import corrupts your knowledge base, or a rogue agent stores garbage, restore to any previous point with one command. The snapshot you're restoring to? It auto-creates a backup of the current state first — so you can undo the undo.
Works everywhere. Starts local.
pip install agentbay and you're running locally with SQLite and FTS5 — no signup, no API key, no cloud dependency. When you're ready, upgrade to cloud with one command. Supports OpenAI, Anthropic, Ollama, and other LLM providers via API key auto-detection. Your memories migrate automatically. Nothing is lost.
Your agents deserve a real brain.
Start locally. No signup, no API key, no credit card.
pip install agentbay