Workshop-forged terminal agent with zero black-box bloat.
Peen-SWE pairs a transparent 100-line Python core with bare bash execution and standard Model Context Protocol (MCP) servers. No hidden prompt rewriting, no stateful shell corruption, and full support for local LLMs.
Three Simple Primitives
No multi-layer agent wrappers or complex graph state. Everything compiles down to plain execution.
Stateless Shell Execution
Instead of holding a fragile pseudo-terminal open, every action executes via an independent subprocess.run or docker exec.
Model Context Protocol
Connect any external tool server (Git, DB, Postgres, filesystem) via stdio JSON-RPC without adding agent-side custom dependencies.
Strict Linear History
No hidden prompts or background summarization routines. The LLM messages match the execution trajectory step-for-step.
Zero Bloat Architecture
Measured against traditional enterprise agents and legacy scaffolds.
| Attribute | Peen-SWE (peen) |
Claude Code | Legacy SWE-agent |
|---|---|---|---|
| Core Agent Code | ~100 lines (Python) | Opaque bundle (TS) | ~3,500 lines |
| Shell Management | Stateless subprocess.run |
Stateful PTY | Stateful session |
| Tool Protocol | Native Bash + MCP 2.0 | Hardcoded tool set | Custom tool configs |
| Local Model Support | Native (Ollama, vLLM, LM Studio) | No (Anthropic only) | Complex config |
| Startup Overhead | < 100ms | 1 - 2s | 2 - 4s |
| Trajectory Inspection | Built-in terminal TUI | Web dashboard | GUI viewer |
Local & Offline Model Support
Run entirely on your own hardware without transmitting proprietary code to third-party APIs.
Ollama / LM Studio (Local OpenAI-compatible)
Zero latency, no rate limits, and zero dollar cost per token.
vLLM High-Throughput Cluster
Batch evaluations at 400+ tokens/sec on local GPU instances.