memoket-kite
An open-source memory engine for AI agents that keeps what it is told as traceable, cited facts instead of fuzzy vector matches, and answers questions with an auditable plan.
View memoket/memoket-kite on GitHub- GitHub stars
- 234
- Forks
- —
- Language
- Python
Project details
- Repository
- memoket/memoket-kite
- Licence
- Apache-2.0
- Primary language
- Python
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.
Explore by topic
More tools in Knowledge & documents
- voicemem
xzf-thu · Apache-2.0
Gives voice assistants a persistent memory that tracks facts and emotional context across conversations, so the assistant gradually gets to know each user, at low…
- daidocs
kerneta · Apache-2.0
Gives your AI assistant a memory that lives as plain .dai files on your own disk, so you can open, grep, and keep it instead of trusting a black-box memory feature.
- claude-mem
thedotmack · Apache-2.0
Gives any AI coding agent persistent memory across sessions: it captures what the agent did, compresses it with AI, and feeds the relevant parts back into future…
- pageindex
vectifyai · MIT
An open-source document index that lets an LLM retrieve the right passages from long documents by reasoning over structure instead of vector similarity search, skipping…