MindGraph gives coding agents durable memory that survives sessions
ShanRizvi · x · 2026-07-29
MindGraph adds durable graph-based memory for coding agents
MindGraph is positioning itself as a persistent substrate for coding agents like Claude Code and Codex.
- The product says coding agents typically lose task context between sessions: objective, plan, failed attempts, and lessons.
- MindGraph stores tasks, iterations, blockers, and learnings as code-anchored graph state so a fresh session can resume exactly where the last one stopped.
- Its demo walks through three sessions: one hits a wall and records a failure, the next resumes cold with only a bounded brief, and the third can query the full history of work.
- The product highlights code-grounded memory, graph-managed work, and deterministic session handoff as its main benefits.
Related event: MindGraph: Persistent Graph Memory for Coding Agents(8 posts)→
More from coding & agent
- Harness open-sources desktop and mobile apps for orchestrating agent fleets across frameworks and machines — dee_hw · 2026-10-16
- Open-Source Google Analytics MCP Server Lets LLMs Query GA Data via Natural Language — modelcontextprotocol · 2026-10-16
- LLM ideation experiment: just ask for non-obvious ideas — and Opus beats smaller models by a wide margin — arjunrajlab · 2026-10-16
- a16z podcast: AI cut a 6-month feature to 10 days and widened engineer gaps 10x — a16z · 2026-10-16
- "Hold On, My Agents Are Freezing My Screen": The Daily Grind of the Agent Era — every · 2026-10-16
- Dev builds MCP feeding Claude 3,000 real launch videos to fix samey AI output — Designer_Landscape25 · 2026-10-16