A coding agent harness for multi-session workflows, featuring semantic memory, multi-agent swarm collaboration, and cross-harness session resume. It targets developers who need to run multiple concurrent agent sessions with reduced RAM usage and faster boot times.
Project overview
Addresses resource overhead and coordination gaps in existing coding agents by embedding semantic memory for automatic recall and enabling multi-agent collaboration within the same repository.
Project type
AI Agent · AI Coding
Use cases
Coding & Development
Deployment
Refer to project documentation
License
MIT
Best for
Developers managing multiple concurrent agent sessions who need semantic recall and multi-agent collaboration.
Users transitioning sessions from other harnesses like Claude Code, Codex, and OpenCode.
Key capabilities
Built for scaling multi-session workflows with optimized RAM usage and fast boot up times.
Embeds each turn/response as a semantic vector to automatically recall relevant information without actively calling memory tools.
Spawn two or more agents in the same repo to automatically manage native collaboration and conflict resolution.
Allows the agent to enter a mode to modify its own source code, build, and test changes automatically.
Provides a side panel for auxiliary information, mermaid diagrams, and info widgets that take up negative space on the screen.
Works with subscription-backed OAuth flows and many provider integrations.
Comes with instructions on how to set up Firefox Agent Bridge for browser automation.
Adds file structure information to the grep return so the agent can infer more of the file without reading it.
Limitations and risks
Agents do not like to commit in a dirty git state with active changes; git was not built for multi-agent workflows.
Weaker models can make subtle, breaking changes when using self dev mode.
Getting started
Install the CLI on Linux, macOS, or Windows using a single curl command (curl -fsSL https://jcode.sh/install | bash) and launch by running jcode.
Alternatives and comparisons
Provides a software development methodology enforcing test-driven development and subagent-driven development for coding agents.
Maximizes performance and consistency across AI agent harnesses like Claude Code and Cursor with reusable skills and security scanning.
Small, composable engineering skills that enforce software engineering fundamentals like test-driven development and domain modeling.