grantai_inferLABSCO SUMMARY
An agent can recall the exact sentence it was told, not something like it.
Memory is addressed rather than searched, so recall returns the stored text verbatim with its source. The shared pool is the other half: several agents write into the same memory, tagged by speaker, and read each other's.
What it is
A local memory store for AI agents. Content is stored under an identifier and retrieved by direct addressing rather than vector similarity, so what comes back is the text that was indexed, with its attribution. It runs on your machine, and storage is local and encrypted.
What you get
- Content stored for later recall, with a source and optionally the agent that said it
- Memory queried for relevant context, filterable by which agent wrote it
- Files or whole directories imported in one call
- Git commit history imported as memory
- Session summaries stored, and conversation turns saved so a new session picks up where the last stopped
- Project state tracked, and code patterns kept as reusable snippets
- A health check on the server
Requirements
Docker, running the published image ghcr.io/solonai-com/grantai-memory — or, on macOS and Linux, the native download from solonai.com installed with install.sh, then a restart of the AI tool you use it from. No account and no key; nothing is sent off the machine.
Setup effort
One command — docker pull ghcr.io/solonai-com/grantai-memory:1.8.6
USE CASES
01
Telling an agent something once and having it stick
Store the fact with a source name, then query for it later by topic and get that sentence back rather than a paraphrase of it.
02
Bringing an existing folder of notes into memory
Import the directory in one call, then query across it — no chunking decisions, no embedding pipeline to tune.
03
Picking a session back up where it stopped
Save the conversation turns and a summary as you go, so the next session starts from what was established rather than from nothing.
04
Giving several agents one shared memory
Each agent writes with its own speaker tag and reads the same pool, optionally filtering recall to what a particular one contributed.
05
Keeping the code patterns your team actually uses
Store the snippet once and recall it by intent, so the pattern comes back as written rather than reconstructed.
06
Letting an agent read the project's own history
Import the commit history and track project state, so "why is this like this" has somewhere to look.
9 tools
Listed in project docs. Your client may show a different list.
grantai_teachgrantai_learngrantai_healthgrantai_summarizegrantai_projectgrantai_snippetgrantai_gitgrantai_captureBEFORE YOU INSTALL
What to know first
Tools you get
9 tools named in the project's documentation.
Requires
docker on PATH
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
docker pull ghcr.io/solonai-com/grantai-memory:1.8.6MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"grantai": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--pull",
"always",
"-v",
"grantai-data:/data",
"ghcr.io/solonai-com/grantai-memory:1.8.6"
]
}
}
}
