Utopia: open-source bitemporal knowledge graph gives RAG agents a memory of change
Shruti_0810 · x · 2026-09-04
The GitHub project Utopia tackles enterprise RAG's memory problem: most systems keep only the latest state, so past facts — status changes, contract updates, policy replacements — simply vanish.
Core idea: a bitemporal knowledge graph
- Tracks both when a fact was actually true and when the system learned it
- Lets agents query "what did we know about this customer 3 months ago?", "what changed between January and March?", or "where did this come from?"
- Also supports entity resolution, conflict detection, derived facts, editable ontologies, and source tracking
Under the hood it uses familiar tools (Postgres, pgvector, Tantivy, RRF, MCP, OpenAI-compatible models); the differentiator is the memory layer, shifting agents from "what's relevant now" to "what did we believe, when, and why it changed."
More from coding & agent
- GPT Sol plays real-time table tennis via latency-aware agent research loop — wzenus · 2026-10-21
- Daytona raises $60M Series B at $1B valuation to build the agent cloud — tsi_org · 2026-10-21
- PostgreSQL 19 slips to November as LLM-assisted code review floods committers with edge cases — sanjaykalra · 2026-10-21
- 9x Vision open-sources video perception for agents: timestamped evidence via MCP and CLI — koto9x · 2026-10-21
- LangChain adds Human-in-the-Loop beta to Managed Deep Agents — LangChain · 2026-10-21
- Voxtral 3 ships a LiveKit-based voice agent SDK streaming listen-think-speak — MistralAI · 2026-10-21