regenrek/peky — All your AI Agents like Claude Code, Codex CLI in a single TUI to keep things organized.

Description and use

**Brief Summary (2‑3 sentences)**
*rekek/peky* is a Go‑based terminal UI that consolidates multiple AI agents—such as Claude, Code, and Codex CLI—into a single, organized workspace. It lets developers stitch isolated prompts and tools together into repeatable, multi‑agent workflows, making it easier to coordinate tool‑use pipelines and maintain agent memory. With 144 ★ on GitHub and recent updates, it offers a lightweight orchestration layer for AI‑augmented development.

**Value**

• **Unified interface:** Eliminates the context‑switching overhead of juggling separate CLIs or web UIs, letting teams manage prompts, responses, and tool calls from one TUI.
• **Workflow repeatability:** By turning ad‑hoc prompt sequences into declarative pipelines, teams can version, share, and reuse agent patterns across projects.
• **Extensibility:** The exposed API/SDK and language‑agnostic metadata make it straightforward to plug in additional models or custom tools, supporting complex multi‑agent orchestrations.

**Practical Adoption Path**

1. **Prototype stage:** Clone the repo, run the provided binary, and connect your existing API keys (Claude, Codex, etc.) to validate the TUI workflow on a small code‑generation or analysis task.
2. **Integration:** Wrap the CLI calls in scripts or CI jobs, or embed the SDK in internal tooling to automate repeatable pipelines (e.g., “lint → generate tests → review”).
3. **Standardization:** Define a repository of shared workflow definitions (YAML/JSON) that teams can version‑control, and use *peky* as the canonical execution environment across dev, QA, and ops.

**Production Readiness**

• **Maturity:** Medium. The project is actively maintained (last commit 2026‑05‑12) and has a modest but growing community (144 ★, 6 forks).
• **Stability:** Core functionality (agent orchestration, TUI, API wrappers) appears stable, but production use should include a dependency audit (Go modules, third‑party SDKs) and security review of the bundled agents.
• **Operational considerations:** Verify licensing compatibility, monitor upstream model API rate limits, and establish a process for updating the binary to incorporate security patches. With these checks in place, *peky* is well‑suited for internal prototypes and can be hardened for production‑grade AI‑driven pipelines.

Problem

regenrek/peky helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

All your AI Agents like Claude Code, Codex CLI in a single TUI to keep things organized.

Source