CrewAI¶

holographic_integrations.crewai provides the two pluggable storage points CrewAI exposes today:

Class	Plugs into	CrewAI interface
`HolographicMemoryStorage`	`Memory(storage=...)` (and `Crew(memory=Memory(...))`)	`crewai.memory.storage.backend.StorageBackend`
`HolographicKnowledgeStorage`	`Knowledge(storage=...)`	`crewai.knowledge.storage.base_knowledge_storage.BaseKnowledgeStorage`

CrewAI replaced its per-memory-type storages (short-term, long-term, entity) with one unified Memory and a StorageBackend protocol. This adapter targets that protocol, not the removed RAGStorage.

Install¶

pip install "holographic-integrations[crewai]"

Run hms-server --input-dim N where N is the length of your CrewAI embedder's vectors. Memory embeds text itself and hands vectors to the backend.

Quickstart¶

from crewai.memory.unified_memory import Memory
from holographic_integrations.core import HmsConfig
from holographic_integrations.crewai import HolographicMemoryStorage

storage = HolographicMemoryStorage(HmsConfig(url="http://127.0.0.1:8080", api_key="...", tenant_id="my_crew", input_dim=1536))
memory = Memory(storage=storage, embedder={"provider": "openai", "config": {"model": "text-embedding-3-small"}})
crew = Crew(agents=[...], tasks=[...], memory=memory)

Knowledge: Knowledge(collection_name="docs", sources=[...], storage=HolographicKnowledgeStorage(config=HmsConfig(...))). The knowledge storage embeds with config.embedder (default: offline HashingEmbedder), so give it the same encoder you want at query time.

A runnable offline example (scripted LLM, hashing embedder) is integrations/python/examples/crewai_memory.py.

Config and knobs¶

All HMS knobs are HmsConfig fields: url, api_key, tenant_id (hard isolation, separate store), collection (soft scope inside a tenant), embedder (only for records that arrive without an embedding), input_dim, zero_trust_key (client-side vector masking, obfuscation not encryption), max_fetch, overfetch. The CrewAI embedder, LLM and scoring weights stay on Memory(...) as usual.

How CrewAI concepts map¶

CrewAI	Stored as
`MemoryRecord.content`	document text
`scope`	`crew_scope` plus one boolean key per ancestor path, so a scope prefix is an equality filter
`categories`	`crew_categories` plus one boolean key per category
`metadata[k]`	`crew_m_<k>`
`importance`, `created_at`, `last_accessed`, `source`, `private`	`crew_*` keys, round-tripped exactly
score	`1 / (1 + sqrt(2 - 2 cos))`, the same formula as CrewAI's LanceDB backend on unit vectors, so `min_score` and the composite recall score keep their scale

Filter mapping¶

`search` / `delete` argument	Evaluated
`scope_prefix`	by the service, before ranking (ancestor keys). Matches on path-component boundaries: `/ops` matches `/ops` and `/ops/deploy`, not `/opsx` (LanceDB's `LIKE 'prefix%'` would match `/opsx`).
`categories=[c]`	by the service
`categories=[a, b, ...]` (any of)	in the adapter, on an over-fetch of `overfetch * limit` candidates (bounded by `max_fetch`)
`metadata_filter`	by the service (equality on every key, as in CrewAI)
`older_than`	in the adapter (delete only)

Limits¶

The service has no list or offset endpoint. list_records, get_scope_info, list_scopes, list_categories and count read at most max_fetch records (default 100, the server's --max-top-k) and emit a UserWarning when truncated. Raise max_fetch together with --max-top-k for larger scopes. search, delete and reset are exact at any size.
touch_records is not implemented (the service does not return stored vectors, so a record cannot be rewritten to update last_accessed); last_accessed is set when the record is saved. CrewAI treats touch_records as optional.
search returns at most max_fetch results.
Embedding dimension must equal --input-dim; a mismatch is a 422 from the service surfaced as HmsError, not CrewAI's EmbeddingDimensionMismatchError.
Text per record is limited to 64 KiB, metadata to 64 KiB.

Sync and async¶

save, search, delete have asave, asearch, adelete counterparts on the async client; the sync methods use a separate sync client. Knowledge storage has asave, asearch, areset as well.

Tested¶

crewai 1.15.28, Python 3.12, against hms-server built from this repo.
Conformance: isinstance(storage, StorageBackend) (runtime-checkable protocol), every protocol method exercised against the real server, Memory.remember/recall(depth="shallow")/forget/info/list_records end to end, Knowledge.add_sources/query end to end, and a real Crew.kickoff() with a scripted BaseLLM: the recalled memory reaches the agent prompt and the task result is saved back through the backend (tests/crewai/test_crewai.py).
Deep recall (depth="deep") and LLM-driven scope/category inference call the LLM and are CrewAI behavior, unchanged by the backend. They need a real LLM and were not run.