Skills SSOT and proving ground for entwurf — one operator's memory, skills, and 1KB identity carried identically across pi, Claude Code, Codex, Antigravity, Copilot, OMP, and OpenClaw. Semantic memory (Qwen3-Embedding-8B + LanceDB), 43 shared skills, and a version-pinned bench for agent runtimes.
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
Open-source, local-first AI coding agent usage and cost dashboard for Claude Code, Codex, Cursor, OpenCode, Kiro, and Pi.
Open-source (AGPL-3.0), self-hosted autonomous coding agent: label a GitHub Issue, get an independently reviewed, merged PR and a tagged release.
A loop-engineering system for AI coding agents, delivered as a Pi package. Converge → specify → implement: parallel TDD development with dual-ring convergence gates, adversarial cross-source review, source-grounded citation verification, and prior-art collision search — honest coverage at every gate, never a silent green.
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents
Manage coding-agent skills, agents, and plugins from one catalog. Supports Claude Code installs and Pi-compatible skill and agent views.
54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.
Claude Code & Pi Coding Agent plugin — senior-engineer toolkit: Clean Architecture, DDD, SOLID, TDD, design patterns, security review, and language expertise across Bash, C#, Dart, Go, Java, Kotlin, Python, Ruby, Rust, SQL, Swift, and TypeScript.
Convert AI coding CLI sessions between Codex, Claude Code, Pi, OpenCode, Devin, and Factory. SDK, CLI, MCP chat recall, and trace export for fine-tuning.
Playwright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.
Docker-isolated Paseo with Pi CLI, persistent state, and Gradle defaults.
Curated, harness-agnostic AI agent skills focused on security, token optimization, and deep web intelligence.
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Portable skills, agents, hooks, and Pi extensions for Claude Code, Codex CLI, Copilot, Cursor, Grok, and Pi.
Multi-harness token-usage cost reporter for AI agent sessions (pi, Claude Code, Codex, opencode). Reads JSONL logs, prices from LiteLLM catalog, auto-refresh built-in. One file, zero deps.
Run and supervise Pi coding agents in visible tmux grids.
Distill your coding-agent sessions from every harness (Claude Code, Codex, pi, Cursor, Copilot, Antigravity) into AGENTS.md + HANDOFF.md, so no decision stays trapped in one harness's memory.
Run Kimi locally on consumer GPUs with high throughput for Aider, Cline, and other coding agents.
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
To associate your repository with the pi-coding-agent topic, visit your repo's landing page and select "manage topics."