Give Your Coding Agents a Memory You Own
- ID
- 21002
- Status
- summarized
- Published
- 03 Sep 2026, 8:00 AM
- Fetched
- 03 Sep 2026, 8:25 PM
- Provider
- Hugging Face Blog
- Category
- developer-ai
- Original URL
- https://huggingface.co/blog/funes
- Source URL
- https://huggingface.co/blog/feed.xml
Summary
- Score
- 7.0
- Created
- 03 Sep 2026, 8:25 PM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
Funes is a single-binary memory layer for coding agents (Claude Code, Codex, pi, Hermes) that indexes session traces locally into a Lance dataset using a pinned local embedding model, then exposes recall and get tools so agents can retrieve past decisions during new sessions. It combines vector and BM25 search with cross-encoder reranking, indexes incrementally, and can optionally sync to a private Hugging Face dataset you own.
Why it matters
If you switch between coding agents or machines and lose the rationale behind past decisions, funes lets your agent self-serve that context mid-conversation without you pasting old session logs. Install is one curl + one 'funes add <agent>' command, and everything runs locally with no ML runtime dependency, so you can try it on an existing project today without cloud costs.
Discussion angle
Is a local trace-indexing memory layer like funes more practical than manually curating context files or CLAUDE.md-style instructions, and what breaks when an agent retrieves a stale rationale from weeks ago and treats it as current truth?