Give your LangChain, CrewAI, Mastra, or AutoGPT agent persistent graph memory via REST.
Wrap POST /ingest and POST /search as tools. Register with your agent executor or LangGraph node.
Expose Graphory as Tools on any crew member. Shared graph memory across agents in a crew.
TypeScript SDK via REST. Call the Graph API from any Mastra workflow or tool step.
Memory plugin pattern. Replace the default memory store with Graphory's persistent graph.
Define Graphory search and write tools as Pydantic AI tool functions. Type-safe memory, free.
Any REST client works. POST /ingest to remember, POST /search to recall, POST /traverse to explore.
Same API for every framework. Save with POST /ingest, recall with POST /search.
Remember
curl -X POST https://api.graphory.io/ingest \
-H "Authorization: Bearer gs_ak_your_key" \
-H "Content-Type: application/json" \
-d '{
"type": "note",
"title": "Acme pricing blocker",
"body": "Sarah at Acme flagged pricing as the blocker in March.",
"date_published": "2026-03-14"
}'Recall
curl -X POST https://api.graphory.io/search \
-H "Authorization: Bearer gs_ak_your_key" \
-H "Content-Type: application/json" \
-d '{"query": "Acme pricing"}'Full reference at docs.graphory.io. Or use the Python SDK: pip install graphory.
Multi-agent crews write to one graph. Every agent reads the same truth - no message-passing gymnastics.
Your agent can follow real business relationships. Not fuzzy retrieval, actual paths.
No embeddings, no hallucinated recall. Exact queries, exact results. Reproducible runs.
Every memory carries a timestamp, a source, and an audit trail. Audit every decision, replay every run.
Deterministic extraction and retrieval, benchmarked against public datasets.
0.9107 accuracy
LongMemEval (agent + MCP)
0.8667 accuracy
LoCoMo-MC10 (agent + MCP)
0.900 F1
BizLineItemBench
Free up to 100K nodes. No credit card.