Suprflo extracts facts from every conversation, stores them with bi-temporal structure, and recalls exactly what your agent needs, when it needs it.
LLMs are stateless. Everything your agent learns about a user evaporates at the end of the context window.
The session ends and everything the user said is gone. They repeat their preferences, their constraints, their history in every single conversation. Nothing compounds.
Stuffing the whole history into the prompt works until it doesn't. A modest 20K-token history costs ~85× more per query than retrieval, and months of usage blow past any context window entirely.
Recall, truth-over-time, and verifiability. The three things memory vendors ask you to pick between.
Facts carry validity windows, never overwrites. Ask what your agent believed on any past date. The audit trail is the data model.
Every raw turn is kept alongside extracted facts. The worst case is "original words retrieved", never "fact silently lost".
Benchmarks run on the open harness, every failure root-caused, label errors audited against source. If it isn’t reproducible, it isn’t on this page.
Measured end-to-end on the open benchmark harness. Same answerer, same judge, every failure root-caused.
Full 10-conversation set, 1,540 questions, single held-out pass. 93.0% source-verified. mem0 publishes 91.6.
Preliminary: 87 of 500 questions (full run in progress). Session-level ingestion, top-50 retrieval.
400 rubric-judged questions across 20 long conversations. Avg rubric score 0.674, zero ingestion errors.
Methodology: mem0's open benchmark suite, Claude Sonnet 4.6 answerer + judge, Claude Haiku 4.5 extraction. Source-verified = every failure audited against the original conversation text; provable label errors credited. Full run logs and failure analyses in the repo.
From single-turn recall to graph traversal and time-travel queries. Every workflow ships in the core platform.
Extract every fact from your chatbot's conversations. Recall the right ones on the next turn.
Remember preferences, allergies, plans, and constraints. Ground every generation in what the user actually said.
Entities are extracted and linked automatically. Query relationships. Traverse the graph for multi-hop questions.
Ask "what did the user believe six months ago?" and get the correct historical state. Nothing is ever destroyed.
Every write goes through six deterministic phases. Every stage is timed and surfaced in the dashboard's pipeline trace.
Suprflo abstracts every provider through a factory pattern. Swap by config, not by rewrite.
Suprflo is built on plain Postgres with full API access to every memory. Bi-temporal history included, feature for feature on par or better.
Straight answers about how the system actually works.