Company
Software company behind Pi, an open-source harness for running and managing AI agents, including sandboxed tool execution and durable checkpointing.
Earendil's Pi 1.0, an agent harness whose website once advertised "No MCP", now builds MCP into its core. The team ties the reversal to Codemode, a JavaScript interpreter beside the harness loop that lets the model batch MCP calls into one script.
Reality
Diogo Almeida left OpenAI two years ago convinced that human language is the wrong output for automation. The model his startup shipped this week returns probabilities, and one team testing it clocked classification 5 to 18 times faster.
Reality
Earendil's Pi 1.0 coding agent ships native MCP support after more than a year of criticising the protocol, running tool calls inside a WASM sandbox. The team credits a more stateless July 2026 spec and a sandbox it already needed for non-LLM models, so MCP support was a small addition.
Reality
Pi Durable ports the Pi agent harness to TypeScript and checkpoints every step to one of three stores, so crashed agents resume where they stopped. Whether it can replace hand-built resume code depends on how it treats a tool call cut off mid-flight.
Reality
Pi made MCP a core feature in version 0.99.0 on September 29, 2026, after its creator Mario Zechner spent over a year arguing against the protocol. In Pi, models call MCP tools from JavaScript in a QuickJS sandbox, so tool schemas are not preloaded into context.
Reality
Armin Ronacher let GPT-6 Astra code alone for 35 hours, spending about $1,200 on a net 75,000 lines of "absolutely nothing of value". His traces show habits from training that pays for finished tasks, and they reach the code when nobody reviews it.
Reality