Free
Full functionality under MIT license. Bring your own API keys for LLM providers. Install via npm, bun, or curl.
A minimal, extensible terminal coding harness — adapt Pi to your workflows instead of the other way around.
Pi is a minimal, extensible terminal coding harness by Mario Zechner and Earendil Inc. — a low-ceremony CLI agent that supports 15+ LLM providers, tree-structured session history, context engineering via AGENTS.md/SYSTEM.md/skills, and a powerful extension API for tools, commands, events, and custom TUI components. Released under MIT, it ships with four operation modes (interactive, print/JSON, RPC, SDK) and a Pi package ecosystem for sharing extensions, skills, themes, and prompt templates.
Full functionality under MIT license. Bring your own API keys for LLM providers. Install via npm, bun, or curl.
Pi is a terminal coding harness built for extensibility — an agent that stays small at the core with radical extensibility through extensions, skills, themes, and prompt templates. Released under MIT by Earendil Inc.
Explicit session IDs for automation, RPC improvements, predictable retries and timeouts
Read tool output, Windows fixes, adaptive thinking
Shrinkwrap, supply-chain hardening, theme detection
npm install -g --ignore-scripts @earendil-works/pi-coding-agent
cd /path/to/project
pi
# First session prompt
Summarize this repository and tell me how to run its checks.
# Switch models mid-session
/model
# Non-interactive mode
pi -p "List all .ts files in src/"
# Reference files with @
pi @README.md "Summarize this"
# Install a Pi package
pi install npm:@foo/pi-tools
# Export session to HTML
/exportPrime Agent is an open-source (MIT) self-improving coding and research harness by Prime Intellect, built on a Recursive Language Model that runs inside a persistent IPython REPL and a Continual Harness that refines its own state via /refine. It took the same frontier weights from 30.2% to 95.5% on ARC-AGI-3 RHAE Best@1, powered daemon-backed sessions, and ships no hosted offering.
OpenCodeReview (ocr) is Alibaba's open-source AI code-review CLI. It reads git diffs and drives an LLM agent through a hybrid architecture where deterministic pipelines handle file selection, rule matching, and comment positioning while the agent does the reasoning. Built on two years of internal use at Alibaba scale, it ships a multi-language ruleset and consumes roughly 1/9 of the tokens of general-purpose agents.
Multiplayer environment from Zed for coding with agents. Threads unify the agent conversation, the code edits, and human review in one shareable artifact, replacing the branch/PR loop. Built on DeltaDB, a CRDT-based version control layer that records every edit between commits alongside the prompts and reasoning that produced them.