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.
ResumeContext
ResumeContext is a shared-memory service for coding-agent projects that archives sessions from supported agents into a searchable project history. Individuals and teams can retrieve prior work through MCP and continue across agents, machines, and usage limits.
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
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
Alternative a ResumeContext
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
GitBot
GitBot is a local browser-based workspace for creating reusable coding bots powered by Claude Code, Codex, or OpenCode. It helps developers run those agents across repository folders with persistent threads and configurable permissions.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
SonOf
SonOf connects to your repo and PM tool, audits the codebase and surrounding product context, and turns approved work into shipped tickets with senior engineering review. It is aimed at founders and engineering leaders who need backlog help without hiring a full team immediately.