ResumeContext icon

ResumeContext

ResumeContext is shared memory for coding-agent projects, archiving searchable sessions so teams can continue work across agents, machines, and usage limits via MCP.

ResumeContext

Shared memory for coding-agent projects

ResumeContext is a shared-memory service for coding agents. It archives agent sessions from a project into one searchable, project-scoped history rather than leaving each session confined to an individual machine, account, or tool. Agents read that history through the Model Context Protocol (MCP).

A local background daemon reads session files from supported agents and syncs them after the project is configured. Team members can then ask their agents about previous decisions, unfinished work, or related sessions, with answers linked to the source session and line when available. This is intended to reduce repeated investigation and make it possible to move work between coding agents without rebuilding context.

Features

Automatic session archiving

A background daemon reads supported coding agents' session histories from local disk and syncs them to the project archive, roughly every 20 seconds after setup.

Shared project memory

Sessions from different people, machines, and supported agents are kept in one project-scoped archive and attributed to the person and machine that recorded them.

MCP-based retrieval

Agents access the archive through MCP and can cite answers back to the originating session and line, making prior reasoning easier to inspect.

Searchable history

The archive can be searched with the full MCP tool set, including search, grep, read, and SQL over project history.

Cross-agent continuity

The same project archive can be connected to another supported agent, account, or machine so work can continue after an agent usage limit or session change.

Per-project agent selection

Agent sources are selected per project, with support for default or custom history directories and commands to list available agents or set sources non-interactively.

Use cases

  • Recover team debugging context

    Ask an agent what a teammate investigated, which fix was applied, or where the relevant evidence appears instead of repeating the same debugging work.

  • Continue work across agents

    Move from one coding agent to another when a usage limit is reached, while keeping the project history available to the replacement agent.

  • Track project progress

    Review sessions across a project to identify completed work, recurring failing tests, overlapping changes, or unresolved blockers without requesting separate status updates.

  • Onboard contributors

    Give a new teammate access to the existing project archive so they can understand prior decisions and investigations from recorded sessions.

  • Consolidate multi-tool workflows

    Use project-level agent selection to archive sessions from different tools or custom history directories while keeping the archive tied to the relevant codebase.

Pros and Cons

Pros

  • Combines sessions from multiple teammates, machines, and supported coding agents in one project archive.
  • Retrieves prior work through MCP with references to source sessions and lines.
  • Runs synchronization in the background at roughly 20-second intervals after setup.
  • Provides search, grep, read, and SQL access to archived project history.
  • Uses project-scoped access controls and read-only agent access; prompt and completion text is excluded from analytics according to the pricing page.

Cons

  • The documented workflow requires Node.js 22 or newer and local access to an agent's session history.
  • Agent support depends on the supported list and the location of each agent's history; unsupported agents or unusual storage paths may require configuration or a support request.
  • The service is currently in beta, and future paid plans are expected, although pricing has not yet been announced.

FAQ

Which coding agents does ResumeContext support?

ResumeContext reads session history from supported agents' local history directories. Supported agents listed in the documentation are Claude Code, Codex CLI, Cursor, and opencode. Nothing is installed into the agent itself; the CLI is configured per project to read the relevant history location.

How do I set up ResumeContext?

Node.js 22 or newer is required. Install the CLI globally, authenticate each machine with `resumecontext auth`, then run `resumecontext init` in the project directory. The setup also connects the agent through MCP; `resumecontext verify` checks the configuration. An initial sync normally runs within about 20 seconds, and `resumecontext sync` forces one immediately.

How does a teammate join an existing project?

Run `resumecontext init` in the project directory to create a new project. If you are joining an existing project in a clone, use `resumecontext accept` instead, since `init` would create a separate project.

Where is archived history stored, and who can read it?

The archive is stored on ResumeContext's servers and scoped to the project. It is readable only by project members. The agent's access is read-only, and removing a teammate ends their access immediately while retaining the sessions they already recorded.

What does ResumeContext cost during the beta?

ResumeContext is free while it is in beta, with no card requirement, trial clock, or stated usage limits during the beta. The company says it will announce pricing before changes and that existing archived projects will continue working.

Quick Facts

Category
Developer Tool
Primary users
Teams and individuals using coding agents
Supported agents
Claude Code, Codex CLI, Cursor, and opencode
Connection method
Model Context Protocol (MCP)
Setup requirement
Node.js 22 or newer; global CLI installation
Beta pricing
Free during beta; no card required