epic

Epic Harness

A multi-tool AI agent harness that learns from every session — 22 skills, autonomous pipelines, and a self-evolving engine.

One harness, six AI tools. Autonomous from spec to PR. Smarter every session.

English | 日本語 | 한국어 | Deutsch | Français | 简体中文 | 繁體中文 | Português | Español | हिन्दी

A multi-tool AI agent harness with 22 skills (8 pipeline + 14 quality gates), a self-evolving engine, unified memory, and a single-command autonomous pipeline (/orbit). Works with Claude Code, Codex, Cursor, OpenCode, and Cline — all sharing the same ~/.harness/ data directory. After each session, the evolve loop analyzes failures, generates targeted skills, and loads them next time.

---

Web Dashboard — auto-launches on session start

10-screen real-time metrics for eval scores, tool stats, orbit pipelines, evolved skills, and hook health. Opens automatically with the first Claude Code session — no manual setup needed.

# Auto-launches on first session (default: http://localhost:7700)
# Configure port or disable in ~/.harness/config.toml:
[dashboard]
port = 7700       # set to 0 to disable auto-launch
auto_open = true  # open browser on first session

Screens: Dashboard · /orbit Pipeline · Skills (22) · Live Agents · Eval & Evolve · Hooks (6) · Integrations (6) · harness-mem · Settings

---

What It Does

One command ships a feature end-to-end. Skills fire without you asking. The agent gets smarter after every session.

$ /orbit "Add JWT auth to the login API"
→ spec approved → go (TDD subagents) → audit (PASS) → ship (PR + CI) → evolve

Or invoke pipeline skills directly:

/spec "Add JWT auth to the login API"   # clarifies requirements → SPEC-*.md
/go                                      # auto-plans → TDD subagents → 4 min
/audit                                   # parallel review + security + tests → PASS
/ship                                    # isolated test → PR → CI green

Skills trigger automatically in the background — no extra commands:

Writing a feature?    → tdd fires (Red→Green→Refactor enforced)
Test fails?           → debug fires (root-cause first, no random fixes)
Touching auth or DB?  → secure fires (OWASP checklist, no shortcuts)
File hits 200 lines?  → simplify fires (extract, rename, reduce)