widemem-ai

active

Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Importance scoring, contradiction resolution, confidence-aware retrieval.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository: github.com/remete618/widemem-ai
License: Apache-2.0
Last update: 2026-10-24
GitHub stars: ★ 50
Homepage: widemem.ai

agent-memory ai-agent ai-memory claude-code embeddings faiss llm llm-memory local-first local-llm long-term-memory mcp

Listed in

github · source

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.