{"version":1,"type":"story","url":"https://digestai.news/story/jevmem-adds-automatic-project-memory-to-claude-code","json":"https://digestai.news/story/jevmem-adds-automatic-project-memory-to-claude-code.json","markdown":"https://digestai.news/story/jevmem-adds-automatic-project-memory-to-claude-code.md","slug":"jevmem-adds-automatic-project-memory-to-claude-code","headline":"Jevmem adds automatic project memory to Claude Code","summary":"Jevmem is an open-source tool that automatically saves decisions, constraints, bugs, and todos from Claude Code chats into a structured markdown file called **JEVMEM.md**. Built on **Jev**, a system by TypeSafe AI, it integrates as a plugin for Claude Code, Cursor, and Codex, marking superseded lines instead of deleting them. The tool uses a lightweight LLM to decide whether to save a turn, with a median decision time of **0.30 seconds**—faster than six current LLMs tested, though less accurate than **GPT-6 Astra** or **Claude Opus 5.5** on save+kind classification.\n\nJevmem includes security features like scrubbing sensitive data (API keys, passwords) and a poisoning gate to block malicious instructions. It supports retries for Jev outages and offers CLI commands for initialization, auditing, and manual memory management. The project is early-stage, with benchmarks limited to held-out turns and no long-term recall testing. Users must provide a **TypeSafe API key** (OpenAI or Anthropic keys are optional).","keyPoints":["Jevmem saves Claude Code chats as structured markdown with timestamps, confidence scores, and superseded-line tracking","Uses a fast, low-cost LLM (Jev) for decision-making, outperforming others in speed but trailing in accuracy","Includes security features like data scrubbing and poisoning gate, but relies on TypeSafe’s terms for retention"],"whyItMatters":"For developers using Claude Code, Jevmem automates project memory capture, reducing manual note-taking and improving context retention. Its speed and cost efficiency make it appealing for real-time workflows, though accuracy trade-offs may limit adoption for critical decisions.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["TypeSafe AI","OpenAI","Anthropic"],"models":["Jev","GPT-6 Astra","Claude Opus 5.5","Claude Fable 5.1","GPT-6 Luna","Gemini 3.8 Flash"],"people":[]},"firstPublishedAt":"2026-09-22T00:00:00Z","updatedAt":"2026-09-22T00:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"github.com","title":"Jevmem – automatic project memory for Claude Code, built on Jev","url":"https://github.com/Avinash-jetwani/jevmem","publishedAt":"2026-09-22T00:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[{"site":"Hacker News","url":"https://news.ycombinator.com/item?id=49846391","points":44}],"thread":null,"cite":{"text":"Digest AI, \"Jevmem adds automatic project memory to Claude Code\", 22 September 2026, https://digestai.news/story/jevmem-adds-automatic-project-memory-to-claude-code","publisher":"Digest AI","title":"Jevmem adds automatic project memory to Claude Code","datePublished":"2026-09-22T00:00:00Z","url":"https://digestai.news/story/jevmem-adds-automatic-project-memory-to-claude-code"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}