Memnest

io.github.Blue-BPublished by GitHub account Blue-Bv0.4.3Updated Oct 31, 2026

Local memory for coding AIs: search past conversations and decisions from the original text.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Local memory server that lets a coding assistant save, search and read past conversations and decisions from the original text.

What you can do
  • Save, search, read, correct and delete memory records, including linking a replacement to the record it supersedes
  • Search across the current workspace and a shared playbook, or deliberately across all projects
  • Read the original source behind a result by ID, optionally comparing attached local code files
  • Store and retrieve credentials in a separate encrypted vault when vault tools are enabled
  • Import selected earlier conversation files and keep one shared store for several coding clients
When to use it
Useful when you want an assistant to recall why a decision was made, which deployment approach was settled on, or what was tried the last time an error occurred. It suits a growing history of conversations you look up on demand rather than a few always-on rules, which belong in an AGENTS.md or CLAUDE.md file.
Requirements
Runs as a local process on macOS on Apple Silicon or Linux with systemd (x86_64 or Arm64, with the stated glibc versions); Intel Macs need a source build. Python 3 is needed for setup. The first write or search downloads an embedding model of about 1.1 GB, and embedding can use about 1.9 GB of RAM. Other MCP clients connect to a local HTTP endpoint on port 3111.
Before you install
Regular memories are not encrypted and redaction only catches known credential patterns; the port should not be exposed to the internet. Deletion is not immediate erasure, since records default to 30 days in trash and backups or external transcripts may retain copies. A cloud AI provider receives retrieved text you send to its model, and web connectors need a public URL that acts as a credential. The installer edits existing client configurations, so back up memory.db and master.key before…

Installation

In SourceWeft

  1. Open Memnest in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

memnest

[memnest logo]

한국어 | Install | Use it | Operations

Your coding AI forgets everything when the session ends. Memnest lets it look up what you decided before, and why, from the original conversation instead of an AI-written summary.

  • Original text, not summaries. No LLM rewrites your history. Saving and searching call no model API, so there is no API key and no extra token bill. Every result carries a source ID you can open.
  • One memory for every coding AI. Claude Code, Codex, Cursor, and pi connect to the same local service. Decide something in Claude Code, look it up from Codex.
  • Stays on your machine. One Rust binary with SQLite and a local multilingual embedding model. Credentials go to a separate encrypted vault.

[Latest release] [npm: pi-memnest] [License: MIT]

Install

bash
curl -fsSL https://raw.githubusercontent.com/Blue-B/memnest/main/core/scripts/install.sh | bash

This installs the latest release for your user, starts the server and conversation watcher, and adds Memnest to the Claude Code, Codex, and Cursor configurations it finds. Existing configuration is backed up first, and the restore command is printed.

Requirements: macOS on Apple Silicon, or Linux with systemd on x86_64 (glibc 2.35+, e.g. Ubuntu 22.04, Debian 12) or Arm64 (glibc 2.39+, e.g. Ubuntu 24.04). Python 3 is needed for setup. The first write or search downloads an embedding model of about 1.1 GB, and embedding can use about 1.9 GB of RAM.

Read the script first, pin a version, or upgrade
bash
curl -fsSL https://raw.githubusercontent.com/Blue-B/memnest/main/core/scripts/install.sh \  -o /tmp/memnest-install.shless /tmp/memnest-install.shVERSION=v0.4.3 bash /tmp/memnest-install.sh --user

Before upgrading an existing installation, back up memory.db together with master.key.

See it work

[One client saves a decision, a separate client retrieves the same record]

Two separate clients, one local store: the record saved through MCP comes back with the same ID from an independent search. Reproduce it on your own machine.

When to use it

Use the accumulated record for questions such as:

Why did we switch task managers? Find the discussion behind that decision.

What deployment approach did we last settle on for this project, and why?

What did we try the last time this error happened?

The AI searches memory, reads the relevant source, and uses it to answer. Results include source IDs so you can check the evidence. These are example requests, not an autonomous demo or a guarantee that an answer will be found.

For a few rules that should apply every time, AGENTS.md or CLAUDE.md is simpler. Memnest is for a growing history of conversations and decisions that you want to look up when needed.

Connect pi

With the core running, install the matching extension:

bash
# Published extension for core 0.4.xpi install npm:[email protected]
# Or connect a reviewed source checkoutpi install ./pi-extension

If Memnest is already registered from another source, remove that registration first to avoid loading it twice. Use /memnest in pi to check the connection. See extension settings.

Local development: vault tool settings

The extension exposes only the five memory tools by default. To let pi store and retrieve credentials with secret_set, secret_get, secret_list, and secret_delete, enable the vault tools before starting pi:

bash
export MEMNEST_EXPOSE_SECRET_TOOLS=1pi

Restart pi after changing the variable; /reload alone cannot change the running process environment. /memnest reports whether the vault tools are available and shows this activation hint when they are hidden.

Other MCP clients connect to http://127.0.0.1:3111/mcp. See connection examples, other environments and source installation, and upgrade and recovery. Intel Macs need a source build.

Use it

Ask your connected AI to look up a previous conversation or decision. Automatic recall is off by default; you can start by requesting a search when you need one. See extension settings to enable automatic recall.

Clients that call tools directly use this flow:

text
memory_search(query="reason for switching task managers")memory_get(id="<ID returned by search>")

Five tools cover saving, searching, reading, correcting, and deleting. Use memory_remember to explicitly save an important decision. When a fact changes, save its replacement with supersedes=<old ID> to link it to the earlier record.

When the host provides the current directory, searches include that workspace and the shared playbook. Specify project=all for a deliberate cross-project search. See source reading for long records and nearby conversation entries.

Conversations from before installation are not all imported automatically. Select the original files you need with history import.

Source-backed coding records (0.4.0)

Save an approach as proposed, failed, or reported success without treating that report as verification. Optionally attach selected local files with memory_remember(code_files=["relative/file"]), then request memory_get(check_code=true) when you want to compare their bytes. Unrelated edits do not trigger warnings. See code evidence.

Optional team access adds named project grants, audit and retention. A free local comparison records where Memnest did and did not perform well; it does not claim universal accuracy superiority.

Important limits

  • Retrieval is not truth checking. Search can miss a relevant record. Memnest cannot determine whether an old decision still holds. A following-source hint is not a verified reply relationship.
  • Capture is selective. It stores visible conversation text, not reasoning, tool traffic, images, or subagent conversations. It does not import ChatGPT's or Claude's built-in memory.
  • Storage is local; your connected AI answers. Default storage/search makes no generative LLM calls. Explicit evidence_only=true opts in to a configured local source-selector model, whose judgment remains unverified. A cloud AI provider receives retrieved text that you send to its model.
  • Regular memories are not encrypted. Redaction handles known credential patterns, not every possible secret. Do not expose port 3111 directly to the internet.
  • A web connector is a network path into your memories. ChatGPT and Grok connectors need a public URL, retrieved text reaches the provider's servers, and that URL acts as a credential. See web connectors.
  • Deletion is not immediate erasure. Records default to 30 days in trash. New plaintext archives are off by default; old archives, backups and external transcripts may still retain copies. See security and deletion limits.

Documentation and checks

One Rust service stores source records in SQLite and searches with BM25 plus local multilingual embeddings. Search indexes can be rebuilt from the source records.

License

MIT © Blue-B

Source: README.md at commit 33ac55f

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the package type cannot run in the sandbox.

Version history

1
  1. v0.4.3LatestOct 31, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts