AI Agent2026
Turns a single research idea into runnable experiments and a conference-ready paper by orchestrating an LLM-driven end-to-end workflow (literature → design → code → sandboxed runs → analysis → writing). Provides human-in-the-loop checkpoints, domain-specialist executors, and multi-layer citation verification.
AI Coding2026
Turns any codebase, docs, or wiki into an interactive knowledge graph for exploration, semantic search, and Q&A. Uses a Tree-sitter + multi-agent LLM pipeline to auto-generate node summaries, guided tours, and diff impact analysis; CLI and dashboard integrations.
AI Model2026
A distilled 26M-parameter encoder–decoder LLM for on-device function-calling and tool use. Uses a pure-attention Simple Attention Network, provides open weights and local finetuning, and targets high-throughput inference on the Cactus runtime.
AI Agent2026
Provides modular “skills” that help designers and engineers audit, find, and improve UI animations and interaction decisions — optimized for use by AI agents or human-in-the-loop workflows. Distills domain-expert rules into actionable SKILL.md modules (review, improve, find opportunities, vocabulary).
AI Client2026
Orchestrates parallel CLI-based AI agents in isolated git worktrees so you can run multiple coding agents side-by-side, review AI-generated diffs, and link PRs/CI to each worktree. Desktop client with a mobile companion and BYO model subscriptions.
AI Agent2026
Orchestrates LLM-powered coding agents in isolated sandboxes to automate code edits and review pipelines. Provider-agnostic (Docker, Podman, Vercel), supports branch strategies, session capture, reusable sandboxes and structured outputs.
AI Coding2026
Review-first terminal diff viewer that opens changesets in an interactive TUI with multi-file review stream, sidebar navigation, and inline AI/agent annotations. Supports split/stack responsive layouts, watch mode, and Git/Jujutsu pager integration.
Hands-on, phase-based curriculum for building end-to-end AI systems from first principles — implement algorithms, run tests, and ship reusable artifacts (prompts, skills, agents, MCP servers) across Python, TypeScript, Rust, and Julia under an MIT license.
AI Agent2026
Defines 10 design principles and reference implementations for building agent-native, token-efficient CLIs that reduce token and turn costs for AI agents; includes the TOON output format, benchmarks (browser and GitHub), and an AXI catalog of tools.
AI Agent2026
Scans AI agent skills for security issues—detecting vulnerabilities, malicious patterns, and supply-chain risks before installation. Combines static AST checks (64 patterns across 16 categories) with optional LLM semantic review, OSV live CVE lookups, and JSON/Markdown/SARIF outputs for CI or manual review.
AI Client2026
Provides a local browser workspace for browsing and managing pi coding agent sessions — real-time chat, model configuration, skill management, and project file preview. Runs from a single npx/global install, scopes file access to the selected project, and follows Git worktrees.