diff --git a/knowledge base/ai/claude/claude code.md b/knowledge base/ai/claude/claude code.md index 9b1373c..443bf4d 100644 --- a/knowledge base/ai/claude/claude code.md +++ b/knowledge base/ai/claude/claude code.md @@ -1,18 +1,14 @@ # Claude Code -> TODO - -[Agentic][agents] coding tool that reads and edits files, runs commands, and integrates with tools.
+[Agentic][ai agents] coding tool that reads and edits files, runs commands, and integrates with tools.
Works in a terminal, IDE, browser, and as a desktop app. - - 1. [TL;DR](#tldr) 1. [Grant access to tools](#grant-access-to-tools) 1. [Using skills](#using-skills) 1. [Limit tool execution](#limit-tool-execution) 1. [Memory](#memory) +1. [Using plugins](#using-plugins) 1. [Run on local models](#run-on-local-models) 1. [Further readings](#further-readings) 1. [Sources](#sources) @@ -113,6 +109,7 @@ Procedure: ```sh claude mcp add --transport 'http' 'linear' 'https://mcp.linear.app/mcp' --scope 'user' + claude mcp add --transport 'http' 'GitLab' 'https://some.local.gitlab.com/api/v4/mcp' --scope 'local' ``` 1. From within Claude Code, run the `/mcp` command to configure it. @@ -169,7 +166,7 @@ Enables AI assistants to analyze AWS costs and usage data through the AWS Cost E
Run as Docker container -FIXME: many of those environment variable are probably unnecessary here. +FIXME: many of those environment variable are probably **not** necessary here. Manually add the MCP server definition to `$HOME/.claude.json`: @@ -299,6 +296,28 @@ TODO Refer [Manage Claude's memory][documentation/manage claude's memory]. +## Using plugins + +Reusable packages that bundle [Skills][using skills], agents, hooks, MCP servers, and LSP configurations.
+They allow extending Claude Code's functionality, and sharing extensions across projects and teams. + +Can be installed at all different scopes. + +
+ Commands + +```plaintext +# Browse, install, enable/disable, or manage plugins +/plugin +``` + +```sh +# Load a local plugin. +claude --plugin-dir './path/to/plugin' +``` + +
+ ## Run on local models Claude _can_ use other models and engines by setting the `ANTHROPIC_AUTH_TOKEN`, `ANTHROPIC_BASE_URL` and @@ -347,7 +366,7 @@ Claude Code version: `v2.1.41`.
- [Website] - [Codebase] - [Blog] -- [AI agents][agents] +- [AI agents] - [Claude Code router] - [Gemini CLI] - [OpenCode] @@ -365,8 +384,10 @@ Claude Code version: `v2.1.41`.
--> +[Using Skills]: #using-skills + -[agents]: ../agents.md +[AI agents]: ../agents.md [Claude Code router]: claude%20code%20router.md [Create custom skills]: create%20custom%20skills.md [Gemini CLI]: ../gemini/cli.md diff --git a/knowledge base/ai/opencode.md b/knowledge base/ai/opencode.md index ff81617..4d35b9c 100644 --- a/knowledge base/ai/opencode.md +++ b/knowledge base/ai/opencode.md @@ -4,6 +4,8 @@ Open source AI coding agent. +Alternative to [Claude Code], [Gemini CLI] and [Pi]. + @@ -125,6 +127,7 @@ opencode agent list [Claude Code]: claude/claude%20code.md [Gemini CLI]: gemini/cli.md +[Pi]: pi.md diff --git a/knowledge base/ai/pi.md b/knowledge base/ai/pi.md new file mode 100644 index 0000000..304e50b --- /dev/null +++ b/knowledge base/ai/pi.md @@ -0,0 +1,169 @@ +# Pi coding agent + +Minimal, customizable, open source terminal coding harness. + +Alternative to [Claude Code], [Gemini CLI] and [OpenCode]. + + + +1. [TL;DR](#tldr) +1. [Using skills](#using-skills) +1. [Further readings](#further-readings) + 1. [Sources](#sources) + +## TL;DR + +Meant to adapt to one's workflow.
+Extensible with TypeScript extensions, skills, prompt templates, and themes. + +Usable in _interactive_, _print/JSON_, _RPC_, and _SDK_ mode. + +Leverages any inference engine and model as a service.
+Authenticates via API keys or OAuth if needed. + +Executes in YOLO mode by default. + +Add custom providers and models via `models.json` or extensions. + +Stores sessions as trees.
+All branches live in a single file. Filter by message type, label entries as bookmarks. + +Comes with a _minimal_ 200 tokens system prompt.
+Allows control of what goes into the context window and how it's managed. + +
+ Setup + +Use `AGENTS.md` for project instructions, conventions, common commands. All matching files are _concatenated_.
+Loads it (fallbacks to `CLAUDE.md`) at startup from: + +- `~/.pi/agent/AGENTS.md` (global) +- Parent directories (walking up from cwd) +- Current directory + +Replace the default system prompt with `.pi/SYSTEM.md` (in project) or `~/.pi/agent/SYSTEM.md` (global).
+Append without replacing via `APPEND_SYSTEM.md` at the same locations. + +Packages install to `~/.pi/agent/git/` (for git-based ones) or global `npm`.
+Use `-l` for project-local installations (`.pi/git/`, `.pi/npm/` in project). + +```sh +# Install. +npm install -g '@mariozechner/pi-coding-agent' +``` + +
+ +
+ Usage + +| Command | Hot key | Action | +| ------------- | ----------- | -------------------------------------------------------------------------------------- | +| `/model` | `Ctrl+L` | Switch models mid-session | +| `/tree` | | Navigate to previous sessions' points | +| `/export` | | Export sessions to HTML | +| `/share` | | Upload a session to a GitHub gist and get a shareable URL that renders it | +| | `Ctrl+P` | Cycle through favorites | +| | `Enter` | Send a steering message (delivered after the current tool, interrupts remaining tools) | +| | `Alt+Enter` | Send a follow-up (waits until the agent finishes) | +| `/skill:name` | | Invoke a skill | + +```sh +# Run interactively. +pi +pi "Some initial prompt" +pi --provider openai --model gpt-4o "Help me refactor" + +# Run in read-only mode +pi --tools 'read,grep,find,ls' -p "Review the code" + +# High thinking level +pi --thinking 'high' "Solve this complex problem" + +# Run headless. +pi -p "query" + +# Output all events as JSON lines to allow for event streams. +pi --mode 'json' + +# List packages. +pi list + +# Install packages. +pi install npm:@foo/pi-tools +pi install npm:@foo/pi-tools@1.2.3 # pinned version +pi install git:github.com/user/repo +pi install git:github.com/user/repo@v1 # tag or commit +pi install git:git@github.com:user/repo +pi install git:git@github.com:user/repo@v1 # tag or commit +pi install https://github.com/user/repo +pi install https://github.com/user/repo@v1 # tag or commit +pi install ssh://git@github.com/user/repo +pi install ssh://git@github.com/user/repo@v1 # tag or commit + +# Update packages. +# Skips pinned ones. +pi update + +# Enable or disable packages. +pi config + +# Test packages without installing them. +pi -e 'git:github.com/user/repo' + +# Remove packages. +pi remove 'npm:@foo/pi-tools' +``` + +
+ + + +## Using skills + +Skills shall follow the [Agent Skills] standard. + +Place skills in `~/.pi/agent/skills/`, `~/.agents/skills/`, `.pi/skills/`, or `.agents/skills/` (from cwd up through +parent directories), or in a pi package to share with others. + +Invoke them via `/skill:name`, or let the agent load them automatically. + +## Further readings + +- [Website] +- [Codebase] +- [What I learned building an opinionated and minimal coding agent] + +### Sources + +- [Documentation] + + + + + +[Claude Code]: claude/claude%20code.md +[Gemini CLI]: gemini/cli.md +[OpenCode]: opencode.md + + + +[Codebase]: https://github.com/badlogic/pi-mono +[Documentation]: https://github.com/badlogic/pi-mono/tree/main/packages/coding-agent#readme +[Website]: https://pi.dev + + +[Agent Skills]: https://agentskills.io/ +[What I learned building an opinionated and minimal coding agent]: https://mariozechner.at/posts/2025-11-30-pi-coding-agent/