LIVE
Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|OpenAI models are coming to Google Cloud21/10/26 · OpenAI|OpenAI details ChatGPT's new advertising infrastructure21/10/26 · OpenAI|Liquid AI unveils LFM3, a base for specialized multimodal models27/10/26 · Liquid AI|US Police Departments Use AI to Flag 'Suspicious' Driving Behavior27/10/26|AllenAI questions whether LLMs can judge research novelty27/10/26 · AllenAI|Open-Source AI Tools Aim to Speed Up Dementia Research27/10/26 · NVIDIA|Solid-state transformers eyed as a fix for AI's power grid bottleneck27/10/26|OpenAI expands Oracle partnership to bring business apps into ChatGPT27/10/26 · OpenAI|OpenAI publishes a page announcing 'GPT-6.1 Terra', with no technical details available26/10/26 · OpenAI|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|OpenAI models are coming to Google Cloud21/10/26 · OpenAI|OpenAI details ChatGPT's new advertising infrastructure21/10/26 · OpenAI|Liquid AI unveils LFM3, a base for specialized multimodal models27/10/26 · Liquid AI|US Police Departments Use AI to Flag 'Suspicious' Driving Behavior27/10/26|AllenAI questions whether LLMs can judge research novelty27/10/26 · AllenAI|Open-Source AI Tools Aim to Speed Up Dementia Research27/10/26 · NVIDIA|Solid-state transformers eyed as a fix for AI's power grid bottleneck27/10/26|OpenAI expands Oracle partnership to bring business apps into ChatGPT27/10/26 · OpenAI|OpenAI publishes a page announcing 'GPT-6.1 Terra', with no technical details available26/10/26 · OpenAI|
MCPRisingofficial publisher

Basic Memory

MCP : Standardises the connection between an AI application and systems that expose tools or data · requires tout client MCP

Agent memory stored as local Markdown files, readable in Obsidian.

The right compromise for anyone who wants transparent agent memory under their own control.

Overall score
8.4 /10
Security: nothing to flag
Utility
6.5
Reliability
10.0
Security
No caveat on record
Ease
5 min · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

AI assistants forget everything between conversations: project context, architecture decisions, personal preferences. Basic Memory solves this by giving your agent persistent memory, stored as readable Markdown files on your own disk.

Concretely, the tool installs as an MCP server and integrates with Claude Desktop, Claude Code, Cursor, VS Code, Codex, or ChatGPT. The agent reads and writes Markdown notes in a local folder, builds a knowledge graph through wikilinks, and retrieves information via semantic or keyword search. Obsidian can open that same folder with no additional setup.

Basic Memory is aimed at developers and advanced users who want full control over their data: everything stays as plain text on their machine, compatible with Git, Syncthing, or any other sync tool. A cloud version at $15 per month adds cross-device sync, automatic backups, and mobile access.

However, the tool is not suited for people looking for a turnkey solution without a command line: the local install requires Python via the uv tool, and configuration involves editing JSON or TOML files.

What it offers

  • ·Persistent memory stored as local Markdown files, readable and editable by both humans and agents.
  • ·Knowledge graph built automatically from wikilinks and observations recorded by the agent.
  • ·Hybrid semantic search (full-text and vector) with optional reranking by a local cross-encoder.
  • ·Native compatibility with Claude Desktop, Claude Code, Cursor, VS Code, Codex, and ChatGPT via the MCP protocol.
  • ·Direct integration with Obsidian: the same Markdown folder serves both the agent and the note-taking app.
  • ·Cross-device sync, backups, and mobile access included in the cloud version. (paid)
  • ·Shared team workspace allowing multiple users and agents to contribute to a common knowledge base. (paid)
  • ·Schema system to infer, validate, and diff the structure of the knowledge base.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
claude-code, obsidian
Host
tout client MCP
Licence
AGPL-3.0

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active
Last release
23 October 2026

Links and repository checked on 25 October 2026 · added on 1 February 2025

How to install Basic Memory

1. Make sure Python 3.12 or higher is available on your machine. 2. Install uv if not already present (https://docs.astral.sh/uv/). 3. Install Basic Memory with the command: uv tool install basic-memory --prerelease=allow 4. Add the MCP configuration to your AI client's config file (e.g. claude_desktop_config.json for Claude Desktop). 5. Restart your AI client; notes will be stored in ~/basic-memory by default. 6. To use Obsidian, point it at the ~/basic-memory folder: no additional configuration is needed.
uv tool install basic-memory --prerelease=allow

In the same category

Whole category Feed (memory, context) →