Thomas Claburn writes that the Pi coding agent hit its 1.0 milestone with a notable reversal on Model Context Protocol (MCP) support, which its creator Mario Zechner previously dismissed as unnecessary. Earendil, the company that acquired Pi in April 2026, attributed the about-face to improvements in MCP and the developers' own changes that made integrating other capabilities easier. The release also introduced Pi Durable, a separate component for orchestrating long-running agentic applications that was split out to preserve Pi's minimalist design.
- Earendil was formed by Armin Ronacher and Colin Daymond Hanna.
- The MCP changes also enable easier use of the Jev decision model within Pi.
- Pi is described as the Flask of agent harnesses (minimal and extensible), contrasted with Django.
- New features include Codemode (a sandbox for tool calls), virtual model support, deferred tool loading, and cache warming for Anthropic models.
- Earendil was formed by Armin Ronacher and Colin Daymond Hanna.
- The MCP changes also enable easier use of the Jev decision model within Pi.
- Pi is described as the Flask of agent harnesses (minimal and extensible), contrasted with Django.
- New features include Codemode (a sandbox for tool calls), virtual model support, deferred tool loading, and cache warming for Anthropic models.
Richard Gill writes about his personal Pi coding agent setup, which utilizes OpenAI Codex Sol and Astra models at medium and high thinking levels while adhering to Pi's philosophy of simplicity. He relies primarily on `AGENTS.md` files and custom skills rather than complex configuration.
- Commands taking over 30 seconds automatically move to the background to prevent the agent from getting stuck
- The `sub-pi` extension enables spawning new Pi windows and worktrees via tmux
- Slash commands like `/diff` inject command output directly into context without triggering an LLM turn
- Context files and skills traverse parent directories up to `$HOME`
- Commands taking over 30 seconds automatically move to the background to prevent the agent from getting stuck
- The `sub-pi` extension enables spawning new Pi windows and worktrees via tmux
- Slash commands like `/diff` inject command output directly into context without triggering an LLM turn
- Context files and skills traverse parent directories up to `$HOME`
This paper introduces a new class of "unbounded" spigot algorithms for calculating the decimal digits of $pi$, improving upon the classic Rabinowitz–Wagon method. While previous spigot algorithms required users to commit to a specific number of digits in advance and faced potential errors due to carry-over effects from truncated series, this proposed approach eliminates those limitations by allowing for infinite digit generation given sufficient memory. Although not intended to compete with high-performance state-of-the-art arithmetic-geometric mean algorithms, the author’s method offers a mathematically robust, simple, and incrementally efficient way to produce digits one by one without prior commitment or risk of truncation errors.
pi-autoresearch is an autonomous experiment loop for optimizing various targets like test speed, bundle size, LLM training, or build times. Inspired by karpathy/autoresearch, it utilizes a skill-extension architecture, allowing domain-agnostic infrastructure paired with domain-specific knowledge. The core workflow involves editing code, committing changes, running experiments, logging results, and either keeping or reverting the changes – a cycle that repeats indefinitely. Key components include a status widget, a detailed dashboard, and configuration options for customizing behavior. It persists experiment data in `autoresearch.jsonl` and session context in `autoresearch.md` for resilience and reproducibility.
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries
Mathematicians are using Srinivasa Ramanujan's century-old formulae to push the boundaries of high-performance computing and verify the accuracy of calculations.
