# earendil-works/pi > A TypeScript AI agent toolkit: a unified API across LLM providers, an agent runtime with tool calling, a TUI library, and an interactive coding agent CLI. - Magnitude: 4.0 out of 10 — Steady - Stars: 118,736 total · +202 stars measured 2026-10-29, 00:04–14:31 UTC, ≈ 315 by evening - Star trust: star growth looks organic - Category: AI agents · Language: TypeScript · License: MIT · Created: 2025-08-09 · Last push: 2026-10-29 - GitHub: https://github.com/earendil-works/pi · Page: https://gitnova.dev/en/r/earendil-works/pi ## Useful for - Run the interactive coding agent CLI in the terminal - Connect OpenAI, Anthropic and Google through one unified LLM API - Build a custom tool-calling agent on pi-agent-core ## Why it’s here - Star-counter measurements on 2026-10-29 (UTC), 00:04–14:31: 118534 → 118736 stars (+202). This is the change over that interval. - Estimated end-of-day forecast: about +315 stars, using observed gains and the previous day. - Hacker News: “Pi v1.0.0” — 12 points, 27 days ago. - About 59 forks a day — people are taking the code. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 15,227 - Issues and pull requests: 11,152 - Watchers: 342 - Average over the last week: 247 per day - Usual pace: 295 per day - Latest release: v1.4.0 (2026-10-21) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-04 … 2026-11-02: 268, 311, 247, 279, 347, 291, 286, 266, 333, 260, 305, 320, 243, 224, 257, 289, 304, 270, 273, 196, 189, 222, 265, 298, 244, 143, None, None, None, None ## Magnitude by day, last 14 days 10-14 4.4, 10-15 4.2, 10-18 3.9, 10-19 4.2, 10-20 4.1, 10-21 3.9, 10-22 4.1, 10-23 4.3, 10-24 3.9, 10-25 3.6, 10-26 4.1, 10-27 4.0, 10-28 4.4, 10-29 4.2 ## Hacker News - Pi v1.0.0 — 12 points, 2 comments: https://news.ycombinator.com/item?id=49927682 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-29 14:47 UTC, updated every 30 minutes.