Local-first · Open-source core · Apache-2.0

Stop your agents
repeating mistakes.

Local-first, governed memory for Claude Code, Codex, and Cursor — shared across every session and fully yours, so your agents stop re-breaking what you already fixed. Debug it. Prove it. Purge it.

Hive Console — Observe
Observe
Browse
Provenance
Curator
Audit
Knowledge
Flow
Memory Health
212
memories
3
agents live
1,597
recalls / 30d
dimension coverage
project
88%
subject
71%
recall / day (30d)
3 agents connected

Your agents forget — and re-break what you fixed.

Every session starts cold. The bug you already squashed, the convention you agreed on, the fix you shipped yesterday — gone by tomorrow. A CLAUDE.md rots and drifts out of date; a cloud memory tool hides what it knows and you can't audit it. So the same mistakes keep coming back.

re-breaks fixed bugs forgets your conventions stale, unverifiable facts no idea who wrote what can't prove a deletion

Your agents finally remember.

isanna Hive is a local-first memory substrate for AI coding agents — persistent, searchable, and fully governable. A free, open-source core (Apache-2.0), plus a premium Console for teams who need to trust what their agents know.

Your agents
Claude Code · Codex · Cursor · Copilot
Hive Core
Postgres/pgvector + MCP · free · open source · Apache-2.0
Free · Open source
Hive Console
Governance — the app you're looking at
Premium

A hybrid fusion engine — not a single vector lookup.

Every search runs two retrieval arms in parallel and fuses them — semantic (meaning) and keyword (exact term) — so recall doesn't miss what pure vector similarity would.

Vector HNSW ANN semantic similarity
Keyword pg_trgm · RRF exact terms & ids
Structured org tables roadmap — not yet implemented
Graph entity hops roadmap — not yet implemented
vector + keyword → RRF fuse → hybrid rank (relevance + recency + importance) → top-k → inject

Honest about what's on. Vector + keyword fusion (RRF), the relevance/recency/importance blend, and recall telemetry are default-on for every search — no flag. Opt-in (real, gated): point-in-time recall (HIVEMIND_PIT_RECALL_ENABLED). Roadmap — not yet implemented: structured-table recall, graph-augmented recall, a learned reranker, and reflective retry.

Published agent research keeps finding the same thing: memory of past work measurably improves task success and cuts repeated mistakes.

Reflexion · 91% vs 80% Agent Workflow Memory · +51% Voyager · 15× faster MemGPT · memory OS CoALA · agent memory

Debug, prove, purge.

Seven views, grouped into three simple moves — everything your agents remember, under your control.

Debug
See exactly what your agents remember, and how it gets recalled. Live health, full memory browser, and recall pipeline visualisation.
Observe Browse Flow
Prove
Trace every memory to its origin — a tamper-evident, hash-chained trail. A deletion mints a signed erasure receipt only when the delete and the ledger seal both complete; a partial deletion errors instead of returning a receipt.
Provenance Audit
Purge
Dedup, fix, and organise — and remove what shouldn't persist. A cleaner, lower-noise memory base is what current research points to for keeping recall relevant.
Curator Knowledge
For technical reviewers

Under the hood, recall blends vector, keyword (RRF), structured, and graph signals into a hybrid rank based on relevance + recency + importance. Full implementation evidence is shared directly with reviewers and beta buyers.

Questions, answered.

Is the core really free?

Yes. Hive Core is free and open source under Apache-2.0 (including an explicit patent grant) — self-host the full memory substrate forever, no strings and no telemetry.

Where does my memory live?

On a box you own. Hive is local-first — your agents' memory text isn't routed to an outside service.

Which agents work with it?

Anything that speaks MCP — Claude Code, Codex, Cursor, and more — reading and writing through one governed seam.

Do I need to set up a database?

No. The Console brings up Postgres + pgvector in Docker for you — one image, identical on macOS, Windows, and Linux.

What does the paid Console add?

The governance layer — debug, prove, and purge what your agents know — as a read surface over the same local store.

Memory your agents can trust.

Start with the free core, or apply for the private beta.