Persistent, searchable, auditable memory across sessions. Give your agents the context they need — without bolting together ad hoc vector DBs.
Every new session starts from zero. Agents re-learn the same facts, lose user preferences, and have no record of what happened before.
Context dies at the end of every session. Agents can't build on past interactions or remember what they've already learned.
When an agent acts on a belief, there's no way to trace where that belief came from or whether it's still valid.
Agents operate as black boxes. There's no durable audit trail, no corrections layer, and no way for humans to inspect or intervene.
Teams bolt together vector DBs, Redis caches, and custom retrieval pipelines — each one brittle, unscalable, and unmaintained.
IronRecall is purpose-built for agents — not a general-purpose database with memory bolted on.
Dense vector search + sparse BM25 + entity fusion. Surface the most relevant memories — even when queries are vague or ambiguous.
Separate tiers for facts, events, and procedures. Each stored, indexed, and recalled differently — just like human memory.
Automatically merges, deduplicates, and consolidates memories over time. Agents stay sharp without ballooning storage.
Every memory has a source. Incorrect memories can be quarantined or corrected — with full audit history preserved.
Hard multi-tenant boundaries. Each agent, user, or team gets a fully isolated memory namespace with rate limits and quotas.
IronRecall knows what it doesn't know. Detect missing context before an agent acts on incomplete information.
The entire IronRecall interface builds on two core operations. Simple enough to learn in minutes. Powerful enough to run production agents.
Store an experience, fact, event, or procedure into persistent memory. Embeddings are generated automatically. Provenance is tracked.
Query memory with natural language. Returns ranked, relevant memories using hybrid retrieval — ready to inject into your agent's context.
Production-grade components. No proprietary lock-in. Deploy anywhere with Docker Compose.
Language-agnostic HTTP interface. Integrate with any stack, any framework, any language.
Native Python client with full type hints. Drop it into your agent code in minutes.
First-class support for Claude Desktop and Cursor via Model Context Protocol.
Self-host with Docker Compose. No vendor lock-in. Full control over your data.