Skip to main content

Documentation Index

Fetch the complete documentation index at: https://gump.build/docs/llms.txt

Use this file to discover all available pages before exploring further.

Supported Agents

Gump orchestrates coding agent CLIs. Each agent runs in headless mode inside the worktree. Gump prepares the context, launches the process, streams its output, and collects the result.

Agent table

AgentCLI commandContext fileResumeTokensNative cost
Claude Codeclaude -pCLAUDE.md--resume <uuid>Per messageYes
Codexcodex execAGENTS.mdresume <thread-id>Per turnNo
Gemini CLIgemini -pGEMINI.md--resumeAggregatedNo
Qwen CLIqwen -pQWEN.md--resume <uuid>Per messageNo
OpenCodeopencode runAGENTS.md--session <ses_id>Per step_finishNo
Cursorcursor-agent -p.cursor/rules/*.mdc--resume [chatId]Per messageNo

Using agents in workflows

Reference agents by name in your workflow YAML:
- name: impl
  type: code
  run:
    agent: claude-sonnet
Check which agents are available:
gump models

Compat mode

If an agent provider changes its output format or breaks its CLI, Gump falls back to compat mode: raw stdout (not parsed for metrics), git diff as the source of truth, fresh sessions only. The workflow still works — you just lose granular metrics until the adapter is updated.

Adapter doctrine

“Gump executes agents through their native CLI surface. Each adapter encapsulates provider-specific behavior. Gump never reimplements agent reasoning or tool routing.”

Connector roadmap

WaveAgentsStatus
Wave 1Claude Code, Codex, Gemini, Qwen, OpenCodeAvailable
Wave 1.5Cursor CLIAvailable
Wave 2Aider, Copilot CLI, Amp, Kimi CLIPlanned
Wave 3Trae CLI, Neovate, FetchcoderEvaluating