Star 历史趋势
数据来源: GitHub API · 生成自 Stargazers.cn
README.md

AXI: Agent eXperience Interface

Website X Discord

10 design principles for building agent-ergonomic apps.

AXI — Let's build apps agents love.

AI agents interact with external services through two dominant paradigms today: CLIs which were originally built for humans, and structured tool protocols like MCP. Both impose significant overhead.

AXI is a new paradigm - agent-native CLI tools built from 10 design principles that treat token budget as a first-class constraint.

Results

Browser Benchmark

Evaluated across 490 runs (14 tasks × 7 conditions × 5 repeats) using Claude Sonnet 4.6:

ConditionSuccessAvg CostAvg DurationAvg Turns
chrome-devtools-axi100%$0.07421.5s4.5
dev-browser99%$0.07828.6s4.9
agent-browser99%$0.08824.6s4.8
chrome-devtools-mcp-compressed100%$0.09129.7s7.6
chrome-devtools-mcp-search99%$0.09629.4s7.5
chrome-devtools-mcp99%$0.10126.0s6.2
chrome-devtools-mcp-code100%$0.12036.2s6.4

GitHub Benchmark

Evaluated across 425 runs (17 tasks × 5 conditions × 5 repeats) using Claude Sonnet 4.6:

ConditionSuccessAvg CostAvg DurationAvg Turns
gh-axi100%$0.05015.7s3
gh (CLI)86%$0.05417.4s3
GitHub MCP87%$0.14834.2s6
GitHub MCP + ToolSearch82%$0.14741.1s8
MCP + Code Mode84%$0.10143.4s7

Quick Start

Reference AXI implementations:

See the full AXI Catalog below for all official and community AXIs.

npm install -g gh-axi npm install -g chrome-devtools-axi

Add to your CLAUDE.md or AGENTS.md:

Use `gh-axi` for GitHub and `chrome-devtools-axi` for browser automation.

The 10 Principles

These principles define what makes a CLI tool "an AXI":

#PrincipleSummary
1Token-efficient outputUse TOON format for ~40% token savings over JSON
2Minimal default schemas3–4 fields per list item, not 10
3Content truncationTruncate large text with size hints and --full escape hatch
4Pre-computed aggregatesInclude aggregated counts and statuses that eliminate round trips
5Definitive empty statesExplicit "0 results" rather than ambiguous empty output
6Structured errors & exit codesIdempotent mutations, structured errors, no interactive prompts
7Ambient contextInstall opt-in session integrations first, then offer an on-demand skill
8Content firstRunning with no arguments shows live data, not help text
9Contextual disclosureInclude next-step suggestions after each output
10Consistent way to get helpConcise per-subcommand reference when agents need it

AXI Catalog

Official

Reference implementations maintained by the AXI project, validating the principles across different domains:

AXIDomainWhat it does
gh-axiGitHubIssues, PRs, workflow runs, releases, and more. Wraps the official gh CLI with agent-ergonomic output.
chrome-devtools-axiBrowser automationNavigate, click, fill, and extract with combined operations and query filtering. Wraps chrome-devtools-mcp.
lavish-axiHuman reviewTurns agent-generated HTML artifacts into collaborative review surfaces - annotate, comment, and send feedback back to the agent.

Community

AXIs built and maintained by the community:

AXIAuthorDomainWhat it does
npm-axiSSBrouhardnpmSearch and inspect npm registry packages, versions, dependencies, README previews, and downloads with token-efficient output.
sqlite-axiSSBrouhardSQLiteInspect schemas, sample rows, and run capped read-only SQLite queries with token-efficient TOON output.
slack-axiJarvus InnovationsSlackRead, search, sweep, and safely draft Slack messages with token-efficient output.
gws-axiJarvus InnovationsGoogle WorkspaceGmail, Calendar, Docs, Drive, and Slides behind one command, with multi-account write-safety - drafts mail, never sends.
harvest-axiJarvus InnovationsTime trackingReview, log, and edit Harvest time entries by period - for yourself, your team, a project, or a client.
specopsJarvus InnovationsSpec-driven devSpec-driven development for agents - and a demo of shipping an AXI embedded in a skill, not a standalone npm executable.
gitsheets-axiJarvus InnovationsGit-backed dataRead and mutate git-backed record sheets over the shell - TOON output, idempotent commits.
metabase-axiJarvus InnovationsAnalytics / BIQuery, explore, and export from Metabase over the shell - SQL/MBQL, saved questions, schema introspection, full-data export.
otter-axiJarvus InnovationsMeetingsFind and pull Otter.ai meeting transcripts from the shell - wraps Otter.ai's hosted MCP server as a scriptable, headless CLI.

Built an AXI? Follow the contributor workflow to add it to this list.

Build Your Own AXI

Install the AXI skill to get the design guidelines and scaffolding for building an AXI-compliant CLI:

npx skills add kunchenguid/axi

This installs the AXI skill - a detailed guide with examples for each principle that your coding agent can reference while building. For your own AXI, expose an explicit setup command for session hooks as the primary integration, then ship an installable Agent Skill as a lower-overhead secondary path. Users only need one path, but hooks and skills complement each other when both are available.

Development

Browser Benchmark

The browser benchmark harness lives in bench-browser/. It compares browser automation tools across 16 browsing tasks.

pnpm install # Run a single condition × task pnpm --dir bench-browser run bench -- run --condition chrome-devtools-axi --task read_static_page # Run the full matrix pnpm --dir bench-browser run bench -- matrix --repeat 5 # Generate summary report pnpm --dir bench-browser run bench -- report # Render the social video pnpm --dir bench-browser run render:social

The HyperFrames composition for the social asset lives in bench-browser/social/. Edit social/index.html for the animation and render docs/social/rendered/race.mp4 with pnpm --dir bench-browser run render:social.

Published results (490 runs): bench-browser/published-results/report.md

GitHub Benchmark

The GitHub benchmark harness lives in bench-github/. It runs agent tasks across different interface conditions and grades results with an LLM judge.

pnpm install # Run a single condition × task pnpm --dir bench-github run bench -- run --condition axi --task merged_pr_ci_audit --repeat 5 --agent claude # Run the full matrix pnpm --dir bench-github run bench -- matrix --repeat 5 --agent claude # Generate summary report pnpm --dir bench-github run bench -- report

Published results (425 runs): bench-github/published-results/STUDY.md

Contributing

Contributions targeting main must be submitted through the contributor workflow, which uses no-mistakes and guards release-please-generated files from hand edits.

Links

关于 About

Design principles for agent ergonomics. Higher accuracy with lower token cost than both MCP and regular CLI.

语言 Languages

TypeScript93.7%
HTML4.2%
JavaScript2.1%

提交活跃度 Commit Activity

代码提交热力图
过去 52 周的开发活跃度
67
Total Commits
峰值: 30次/周
Less
More

核心贡献者 Contributors