File-based long-term memory toolkit for AI agents — evolved from the MemoryScope project. Turns conversations and documents into readable, editable, searchable Markdown files linked by wikilinks. Three automated background processes (Auto Memory, Auto Resource, Auto Dream) progressively distil interactions into durable memory nodes and build wikilink relationship graphs over time.
- Storage
- Markdown files with YAML frontmatter and wikilinks serve as the primary storage unit — every memory node is a human-readable, directly editable file. Auto Memory consolidates daily conversations into structured Markdown; Auto Resource ingests uploaded documents; Auto Dream further abstracts and links nodes into a connected knowledge base. Files live on local disk or any mounted path.
- Retrieval
- Progressive hybrid search across three signals: wikilink graph traversal for relationship expansion, BM25 keyword matching, and dense embedding similarity. All three are fused (progressive widening) to return relevant memory nodes for a query. Exposed via a SKILL.md-based CLI integration and a Python API (`reme-ai` package).
- Self-host
- Self-host: moderate
- License
- Apache-2.0
- Pricing
- Open-source Apache-2.0 Python package (`pip install 'reme-ai[core]'`), free to self-host. Requires an OpenAI-compatible LLM endpoint and an embedding API (e.g., Aliyun DashScope). No hosted cloud tier found. · Free / OSS
- GitHub stars
- 3,126
- Last release
- 2026-06-26
- Last commit
- 2026-06-26
- First catalogued
- 2026-06-28
Strengths
- Human-readable storage: every memory is a plain Markdown file — inspectable, editable, and version-controllable by both agents and users
- Progressive hybrid search (wikilinks + BM25 + embeddings) without complex infrastructure — single pip install
- Self-evolving knowledge base via Auto Memory / Auto Dream background processes; works across multiple agent types via SKILL.md integration
- Apache-2.0, actively maintained with frequent releases (v0.4.0.4 as of 2026-06-26); evolved from MemoryScope with broader design
Watch out
- Requires external LLM and embedding API keys (no fully-offline default path)
- MemoryScope lineage branch still exists in the repo; ReMe and MemoryScope diverged — verify which is the authoritative successor for production use
- No hosted cloud option: teams must provision and maintain the storage directory and API keys themselves
Best for
- Personal assistants and knowledge-worker agents that need long-term memory stored in a human-readable, inspectable format
- Workflows where both humans and agents read and write the same memory files (e.g., collaborative knowledge bases)
Benchmark results
No sourced results yet.
Sources
- ReMe README (vendor)
- GitHub API repo metadata (stars, Apache-2.0, v0.4.0.4 release) (third-party)
Last verified 2026-06-28 · updated by discover-frameworks