Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// Software stack

Coding agent workbench

A terminal coding agent with up-to-date docs lookup, semantic code navigation, a shared rules file and usage tracking.

6 pieces5 setup stepsscenario: Share rules and skills across agents

What goes in it

  1. 1

    Claude Code Coding agents & AI IDEs Closed / commercial

    Main coding agent

    Anthropic's terminal coding agent, also available on desktop, web and IDEs.

    ★ 153k
  2. 2

    OpenAI Codex optional Coding agents & AI IDEs Open source

    Second agent for cross-review

    OpenAI's coding agent across CLI, IDE extension, cloud tasks and desktop app.

    ★ 130k
  3. 3

    context7 MCP servers & SDKs Open source

    MCP server for up-to-date library docs

    Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

    ★ 63k
  4. 4

    serena Code intelligence Open source

    LSP-based semantic code search and editing

    A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

    ★ 31k
  5. 5

    agents.md Protocols, specs & agent payments Open source

    Rules-file convention shared across agents

    AGENTS.md — a simple, open format for guiding coding agents

    ★ 25k
  6. 6

    ccusage Model gateways, routing & usage Open spec

    Tracks Claude Code usage and cost

How to set it up

  1. 01Install Claude Code as the main agent and Codex CLI for second opinions
  2. 02Write one AGENTS.md at the repo root (build and test commands, conventions) shared by both agents
  3. 03Add the Context7 MCP server for current library docs and Serena for semantic code navigation
  4. 04Have the agent run tests before every change, and let the other agent review the diff
  5. 05Check usage weekly with ccusage to see whether your plan tier fits

✓ Good fit

  • Terminal users doing large, multi-step changes

✗ Look elsewhere if

  • Prefer in-IDE completion and visual diffs: see the AI coding workflow stack (Cursor)

Similar stacks: what’s different

Data updated: AI software & hot ranks · Solutions & stack guides(UTC+8)