kai

Inspect and analyze codebases using pygount for LOC counting, language breakdown, and code-vs-comment ratios. Use when asked to check lines of code, repo size, language composition, or codebase stats.

Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.

Production-grade PR review with execution-verified suggestions. Reads repository conventions, history, and security surfaces before reviewing. For every suggested fix, attempts to compile and test it in the sandbox — the comment includes proof. Modelled on GitHub Copilot's agentic architecture with one critical advantage: the sandbox is already running.

Create, manage, triage, and close GitHub issues. Search existing issues, add labels, assign people, and link to PRs. Works with gh CLI or falls back to git + GitHub REST API via curl.

Open and manage GitHub pull requests through Kai MCP tools — propose changes, monitor CI, iterate on failures, and merge. No git tokens are shared to the sandbox; every GitHub operation goes through the backend via the workspace's GitHub App installation.

Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.

One-time repository onboarding for PR review — builds a RepoProfile (conventions, hot files, security surfaces, nit catalogue, test command) stored as workspace learnings. Re-runs automatically when the profile is stale (>30 days or >30% of files changed).

Manage AWS services for ML workflows including S3, ECR, SageMaker, and EC2

Browse, download, and deploy models, datasets, and spaces on HuggingFace Hub

Define, deploy, and inspect Modal — serverless GPU functions, endpoints, volumes, and existing workspace deployments; also the default GPU runtime for Kai evaluators

Manage GPU pods, deploy serverless endpoints, and run inference workloads on RunPod

Track experiments, log metrics and artifacts, and compare runs with Weights & Biases

Write, test, and upload custom evaluators for code optimization — the fitness functions that drive optimization quality, including the Modal-first GPU evaluator pattern

Get the LLM models for evolutions from the workspace agent subscription tier config

Full code optimization workflow - from analyzing code to running optimization and reviewing results

Produce or update the workspace brief — load context, identify focus repo + user lean, cross-reference activity into Kai-relevant action items, synthesize, save

Daily autonomous work cycle — check workspace state, propose tasks, execute approved work, save a dashboard briefing

Seed Kai's memory on a fresh local install — infer who the user is and what the project(s) are from the workspace + git (single repo or a multi-repo parent dir), ask only what can't be inferred, and commit durable facts via the memory tool so future sessions start with context instead of a blank slate

Kai joins the team — onboards through GitHub data (repos, team, recent PRs, branches, conventions), then publishes an initial briefing with proposed action items

Analyze AWS costs, find waste, and recommend optimizations using read-only MCP tools

Monitor and analyze AWS infrastructure performance using read-only MCP tools

Set up automated recurring code audits and optimization monitoring with cron jobs

How to use Kai platform tools — LOAD THIS FIRST before running any audit, optimization, or repo management operation

Monitor Railway projects, diagnose deployment failures, and audit infrastructure using read-only MCP tools

Analyze Vercel serverless functions, identify expensive code, and optimize it via Kai Evolve

Autonomous periodic codebase hygiene — find structural problems (redundant helpers, dead code, incomplete features, premature abstractions, inconsistent patterns) and propose focused fixes as GitHub issues

Fast, opinionated first-pass assessment of a connected repo — stats, security surface, code health, architecture, AI code smell — delivered as a severity-ranked report with actionable follow-ons

Research and explain Kai outputs - find academic papers, benchmarks, and prior art that explain WHY results work

Full code audit workflow - from adding a repo to reviewing vulnerabilities and filing issues

Run a local kai-security audit with the security_scan plugin tool and act on the findings (local-first, no cloud backend)

Detect codebase patterns — commit velocity anomalies, codebase drift, and dependency risks — and persist them as workspace learnings

Prioritize and explain security vulnerabilities found by Kai scans with research context

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Kai Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

Edit PDFs with natural-language instructions using the nano-pdf CLI. Modify text, fix typos, update titles, and make content changes to specific pages without manual editing.

Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.

Search and retrieve academic papers from arXiv using their free REST API. No API key needed. Search by keyword, author, category, or ID. Combine with web_extract or the ocr-and-documents skill to read full paper content.

Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Use the Python DDGS library or CLI to search, then web_extract for full content.

Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.

Use when completing tasks, implementing major features, or before merging. Validates work meets requirements through systematic review process.