Graphiti Reviews

GitHub Reviews

1. Reinhard

   · Boss at CLOUD Meister · over 5 years ago
   perfect 4 open Source

Graphiti mentions (9)

• Your AI Agent Forgets Everything After Every Session. Graphiti Fixes That.

  Graphiti is an open-source framework by Zep for building and querying temporal context graphs for AI agents. It's the engine behind Zep's managed memory platform, but it's fully usable standalone. - Source: dev.to / about 1 month ago

• I Tested 33 AI Memory Engines — Here's What Actually Works

  Graphiti by Zep is the temporal knowledge graph. Its core insight: knowing the current state isn't enough. You need to know when things changed and what was true before. - Source: dev.to / 2 months ago

• I Built Two Ollama Tools I Don't Actually Need Yet

  Several services share the same Ollama instance on a dedicated host that homelab-agent is provisioning: LibreChat for interactive chat, a SearXNG MCP server for ML-reranked search, and three background embedding jobs — graphiti, jobsearch-mcp, and memsearch-watch. - Source: dev.to / 3 months ago

• I Benchmarked Graphiti vs Mem0: The Hidden Cost of Context Blindness in AI Memory

  It started with a 35,000-token "Master Prompt" that she maintained manually in Notion. Every time something changed in her life, she updated it by hand. That obviously didn't scale. So I moved to Graphiti, a knowledge graph framework that extracts entities and relationships from conversations automatically. - Source: dev.to / 4 months ago

• Show HN: A file-based agent memory framework that works like skill

  - *[Zep](https://github.com/getzep/graphiti)* uses graphs, which handle structure well but add complexity and maintenance overhead. - Source: Hacker News / 7 months ago

GitHub mentions (2473)

• Superlogical – Mitchell Hashimoto

  Is published at https://github.com/.keys so an SSH server to which you connect could do a reverse lookup. This is the reason why my ~/.ssh/config has those 2 lines at the end:

          Host *.

  - Source: Hacker News / 3 days ago

• Your Agent's Confidence Score Is Not a Probability

  All of this assumes you can actually inspect what the agent did — the real inputs after resolution, the real tool outputs, the real intermediate steps. That is the other half of the workflow. AgentLens captures the trace: every model and tool step, resolved inputs, raw outputs. agent-eval scores and gates the output; AgentLens gives you the unforgeable, agent-didn't-author trace data for Tier 1+2 to score against... - Source: dev.to / 3 days ago

• Foreman 101: agentic coding as Kubernetes resources

  # git: the API token, plus the credential used for the push Kubectl create secret generic foreman-github \ --from-literal=GITHUB_TOKEN="$GITHUB_TOKEN" -n foreman-system Kubectl create secret generic foreman-git-credentials \ --from-literal=token="$GITHUB_TOKEN" -n foreman-system Helm upgrade foreman llmkube/foreman -n foreman-system --reuse-values \ --set agent.githubToken.secretName=foreman-github \ ... - Source: dev.to / 4 days ago

• Stop Judging Every Run: Eval Sampling Is a Budget Decision, Not a Coverage One

  This is why eval and observability ship as a unit, not as separate purchases. agent-eval scores and gates the output — the tiers above, drift, hallucination. AgentLens captures the trace of how the agent got there: every model step and tool call, the resolved inputs, the raw outputs, the trajectory. Two things fall out of that:. - Source: dev.to / 13 days ago

• Claude Code permission rules: how allow, deny, and ask actually match

  The real fragility is in trying to constrain arguments. The docs are explicit that a pattern like Bash(curl http://github.com/ *) fails to do what it looks like it does. It won't match curl -X GET http://github.com/... (option before the URL), curl https://github.com/... (different protocol), curl -L http://bit.ly/xyz (redirects to GitHub), URL=http://github.com && curl $URL (variable), or curl http://github.com... - Source: dev.to / 15 days ago