Agent memory that keeps every correction with its history, plus saved working state so a crashed run can resume.
Most agent memory tools overwrite a fact when it changes. Recall treats a correction as a new record. Ask what the agent believes about your editor and it can answer now, as of a past date, and with what the answer replaced. The Recall MCP server is one face of a Go library and a recall binary that also serves HTTP, alongside a Python client.
A memory is a subject, a predicate and a typed value. Predicates sit in a registry that sets their type, whether they hold one value or many, and which ones contradict each other. Forgetting records a withdrawal rather than deleting anything. Starter registries exist for coding, assistant, support, sales and voice agents. If you would rather not define predicates, an open vocabulary lets first use define them. With an extraction model configured, the MCP tools take plain text: remember, recall and forget. Without one, recall mcp -typed serves typed tools instead.
The second half, currently beta, records where an agent is: goal, plan, progress, verbatim turns, pointers to branches or processes, and each world-touching tool call, logged before it runs. A new process resumes from those records within a token budget, and any action left unfinished shows up as unconfirmed rather than being repeated. A lease ensures one process acts for an agent at a time. The MCP tools here include agent_resume, update_working_state, record_turn and begin_action.
Install via pip install polign-recall, Homebrew, or go install, then register recall mcp -write with your client. With nothing configured, memory sits in a local database under ~/.local/share/recall, shared by every agent on the machine, and no model or API key is required to start. To use infrastructure you already run, set RECALL_BACKEND and RECALL_BACKEND_URL:
| Backend | Keyword search | State API |
|---|---|---|
| local (default) | yes | yes |
| polign_db | yes | yes |
| PostgreSQL + pgvector | yes | yes |
| MongoDB | yes | yes |
| Qdrant | no | no |
For many agents, recall serve holds the database credentials and hands each agent a namespaced key.
Release builds send an anonymous usage heartbeat with version, platform and operation counts; RECALL_TELEMETRY=0 or DO_NOT_TRACK=1 disables it. The State API is still beta. Browse our other integrations or see comparable tools in that category.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| remember | Stores a fact, as plain text when an extraction model is configured. |
| recall | Answers what the agent currently believes, with what each answer replaced. |
| forget | Records a withdrawal of a fact without deleting its history. |
| agent_resume | Resumes an agent from its recorded state within a token budget, taking a lease. |
| update_working_state | Updates the agent's goal, plan, progress and related working state. |
| record_turn | Stores a conversation turn verbatim. |
| begin_action | Records a world-touching tool call before it runs so a crash leaves it visible. |
{
"mcpServers": {
"recall": {
"command": "recall",
"args": [
"mcp",
"-write"
]
}
}
}Install first with pip install polign-recall, brew install polign/tap/recall, or go install.
| Variable | Description | Required |
|---|---|---|
| RECALL_BACKEND | Storage backend: local (default), polign, pgvector, mongodb or qdrant. | Optional |
| RECALL_BACKEND_URL | Directory or connection URL for the chosen backend. | Optional |
| RECALL_URL | Address of a recall serve instance, used by recall connect. | Optional |
| RECALL_API_KEY | Recall key for a recall serve instance, used by recall connect. | Optional |
| RECALL_TELEMETRY | Set to 0 to turn off the anonymous usage heartbeat. | Optional |
Run an Actual Budget ledger from your AI agent, with phone approvals for every change on paired machines.
An Odoo module that serves a read-only MCP endpoint at /mcp, scoped to each user's own access rights.
Open-source screen recorder and editor whose MCP server lets an agent record, edit and export a demo video.
Lets coding agents run dev servers and workers as real systemd, launchd or Windows services, and read their logs.
Five npm MCP servers for Yandex Wordstat, Search, Webmaster, Metrika and Direct, for SEO and ads work in the Russian market.
Targeted .NET assembly inspection for AI agents on Windows: find types, decompile one method, trace callers.