GumpGUMP

Stop babysitting your agents.
Engineer their execution.

GitHub Actions for coding agents. With stats.

Define workflows in YAML. Gump validates every step, retries on failure, and tracks what it costs.

brew install isomorphx/tap/gump

MIT License·Agent-agnostic·Git-native

🍿 gump run spec.md --workflow tdd

→ Step 1: Decompose

→ Step 2: Build (3 items)

→ Step 3: Quality

✓ Build: 3 items passed (2 retries, 1 escalation)

✓ Quality: compile + lint + test

✓ Cost: $1.42 · 12 turns · 47s

Every run produces a full trace — what ran, what failed, what it cost.

BUILD YOUR OWN WORKFLOW

Define how agents work.

Use simple YAML to define multi-step workflows. Pick agents, set gates, chain steps. Share them, version them, run them anywhere.

name: cheap2sota
max_budget: 8.00

steps:
  - name: decompose
    agent: claude-sonnet
    output: plan
    prompt: |
      Decompose {spec} into independent items.
      Each item must be implementable and testable in isolation.
    gate: [schema]

  - name: build
    foreach: decompose
    steps:
      - name: impl
        agent: qwen
        output: diff
        prompt: |
          Implement: {item.description}
          Files: {item.files}
        guard:
          max_turns: 60
        gate: [compile, test]
        on_failure:
          retry: 5
          strategy:
            - same
            - same
            - "escalate: claude-haiku"
            - "escalate: claude-sonnet"
            - "escalate: claude-opus"

  - name: quality
    gate: [compile, lint, test]

ORCHESTRATE ANY AGENT

Codex
Codex
Claude Code
Claude Code
Gemini CLI
Gemini CLI
Qwen CLI
Qwen CLI
OpenCode
OpenCode
Cursor
Cursor

6 adapters today. More coming.

Model-agnostic by design.
Match the right tool to the right task.

Don't lock your workflow into a single ecosystem. Balance cost, speed, and reasoning by mixing specialized models.

Decompose with Opus. Implement with Qwen. Review with Gemini.

Gump orchestrates them all seamlessly.

VALIDATE EVERY STEP

Gates verify. Guards protect. Retries fix.

Every step passes through deterministic gates — compile, test, lint, schema checks. No LLM in the loop. If a gate fails, Gump retries with the same agent, escalates to a stronger model, or restarts from an earlier step.

Live guards watch agents in real-time, cutting them off if they blow the budget or write where they shouldn't. Every run executes in an isolated Git worktree. Your main branch stays clean.

Resume a crashed run. Replay from any step.

Step 2: Build — item 1/3
✗ gate failed: test (claude-haiku)
  retry 2/5 (same)
✗ gate failed: test (claude-haiku)
  retry 3/5 (escalate: claude-sonnet)
✓ gate passed (claude-sonnet)

Step 3: Quality
✓ compile + lint + test

Run completed. $1.42 · 47s

KNOW WHAT YOUR AGENTS COST

Run: run_2026_03_23_1842
Workflow: tdd · Status: pass · Duration: 47s · Cost: $1.42

Step            Agent           Turns  Cost    Gate
───────────────────────────────────────────────────────
decompose       claude-opus       3   $0.31   schema ✓
build/1/tests   claude-haiku      8   $0.12   compile+test ✓
build/1/impl    claude-haiku     14   $0.18   compile+test ✓
build/2/tests   claude-haiku      6   $0.09   compile+test ✓
build/2/impl    claude-sonnet    12   $0.44   compile+test ✓ (escalated)
quality         —                 —   —       compile+lint+test ✓

Structured execution data. Not just logs.

Every run produces a rich event ledger — cost per step, token usage, turns, retries, time-to-first-diff. Not reconstructed after the fact. Tracked live, from the agent stream.

Know which agent fails on which kind of task. Know when to escalate. Know what you're spending.

spec → step → agent → attempt → metrics

Run it. Measure it. Ship it.

brew install isomorphx/tap/gump