Pi Coding Agent - Revision history

Davrot@uni-bremen.de: /* Multi-Agent */

2026-08-10T16:05:39Z

Multi-Agent

← Older revision		Revision as of 16:05, 10 August 2026
Line 79:		Line 79:
	</syntaxhighlight>		</syntaxhighlight>

	== Multi-Agent ==		== Multi-Agent Workflows with <code>pi-subagents</code> ==
	~~It is highly useful~~ to ~~use multi~~-agents ~~because the other agents have their~~ your ~~context window. Go into your project folder, start pi~~ and ~~tell it to create an AGENTS.md~~. ~~Explain it what the project is about and that~~ you ~~want to use~~ sub-~~agents to deal with the~~ context ~~limit of the model~~. ~~It should create~~ the ~~AGENTS.md~~ and ~~one md file for every type~~ of ~~sub~~-agent.		Delegating work to sub-agents keeps your main session clean and scalable. When you delegate a heavy task—such as searching a large codebase, inspecting logs, or analyzing dependencies—the sub-agent executes it in its own isolated context window. Once finished, it returns only the final summary to your main session, keeping all intermediate detail and token bloat out of your primary conversation history.<blockquote>'''Note:''' Sub-agent capabilities require the '''<code>pi-subagents</code>''' extension documented earlier on this page. They are not enabled in base Pi by default.</blockquote>

	~~Then tell pi to read the AGENTS.md (it is a good idea to tell pi this at every start of a new session :~~-~~) )~~		==== Setting Up Project-Local Sub-Agents ====

	~~You should tell pi~~ to ~~put also information~~ to AGENTS.md ~~that you don~~'~~t want~~ to ~~tell it again~~ and ~~again about~~ the project.		# Open your project directory and launch Pi.
			# Prompt Pi to generate an <code>AGENTS.md</code> file along with initial agent definitions tailored to your stack.
			#* ''Example prompt:'' <code>"Analyze this project and generate an AGENTS.md outlining our agent architecture, plus sub-agent definitions for scout, worker, and reviewer roles."</code>
			# Pi will create <code>AGENTS.md</code> in your project root, along with individual sub-agent configuration files in your project's <code>.pi/agents/</code> directory (e.g., <code>.pi/agents/scout.md</code>, <code>.pi/agents/worker.md</code>).

			==== Agent Configuration & File Locations ====
			Sub-agents use Markdown files with YAML frontmatter to define their prompt instructions, tool permissions, and model parameters:

			* '''Project-Specific Agents:''' <code>.pi/agents/*.md</code> (scoped to the current repository; checked into Git so the whole team benefits).
			* '''Global Agents:''' <code>~/.pi/agents/*.md</code> (available across all projects on your machine).

			==== Best Practices for Session Workflows ====

			* '''Include <code>AGENTS.md</code> in your opening prompt:''' Start new sessions with a standard directive like <code>"Read AGENTS.md first to load project context."</code> This instantly grounds Pi in your team's workflow without manual setup each time.
			* '''Persist project knowledge:''' Instruct Pi to update <code>AGENTS.md</code> whenever core architecture, technology choices, or coding conventions evolve. Treating <code>AGENTS.md</code> as living documentation ensures future agent sessions stay aligned without repeated prompt engineering.

Davrot@uni-bremen.de: /* tmux */

2026-08-10T16:01:19Z

tmux

← Older revision		Revision as of 16:01, 10 August 2026
Line 78:		Line 78:

	</syntaxhighlight>		</syntaxhighlight>

			== Multi-Agent ==
			It is highly useful to use multi-agents because the other agents have their your context window. Go into your project folder, start pi and tell it to create an AGENTS.md. Explain it what the project is about and that you want to use sub-agents to deal with the context limit of the model. It should create the AGENTS.md and one md file for every type of sub-agent.

			Then tell pi to read the AGENTS.md (it is a good idea to tell pi this at every start of a new session :-) )

			You should tell pi to put also information to AGENTS.md that you don't want to tell it again and again about the project.

Davrot@uni-bremen.de: /* Update extension */

2026-08-10T15:33:50Z

Update extension

← Older revision		Revision as of 15:33, 10 August 2026
Line 44:		Line 44:
	=== Update extension ===		=== Update extension ===
	<syntaxhighlight lang="bash">pi update --extensions</syntaxhighlight>		<syntaxhighlight lang="bash">pi update --extensions</syntaxhighlight>

			== Academic Cloud ==
			~/.pi/agent/models.json<syntaxhighlight lang="json">
			{
			"providers": {
			"academiccloud": {
			"baseUrl": "https://chat-ai.academiccloud.de/v1",
			"api": "openai-completions",
			"apiKey": "<your-academiccloud-api-key>",
			"models": [
			{
			"id": "qwen3-coder-next",
			"reasoning": false,
			"compat": {
			"thinkingFormat": "qwen"
			},
			"contextWindow": 262144,
			"maxTokens": 262144
			}
			]
			}
			}
			}
			</syntaxhighlight>

			== tmux ==
			If you want to use tmux as terminal then you need to set

			.tmux.conf<syntaxhighlight lang="bash">
			set -g mouse on
			set -g extended-keys on
			set -g extended-keys-format csi-u

			</syntaxhighlight>

Davrot@uni-bremen.de: /* Extensions */

2026-08-10T15:25:46Z

Extensions

← Older revision		Revision as of 15:25, 10 August 2026
Line 34:		Line 34:

	'''pi-hermes-memory''' — Gives Pi persistent memory across sessions: it remembers facts, corrections, and past failures, supports full-text search over old conversations ("what did we discuss about auth?"), and scans everything it stores for secrets before saving. Install it if you're tired of Pi forgetting everything each time you start a new session.		'''pi-hermes-memory''' — Gives Pi persistent memory across sessions: it remembers facts, corrections, and past failures, supports full-text search over old conversations ("what did we discuss about auth?"), and scans everything it stores for secrets before saving. Install it if you're tired of Pi forgetting everything each time you start a new session.

			In ~/.pi/agent/settings.json I am replacing "npm:pi-agent-extensions", with<syntaxhighlight lang="json">{
			"source": "npm:pi-agent-extensions",
			"extensions": [
			"!/whimsical/"
			]
			},</syntaxhighlight>

	=== Update extension ===		=== Update extension ===
	<syntaxhighlight lang="bash">pi update --extensions</syntaxhighlight>		<syntaxhighlight lang="bash">pi update --extensions</syntaxhighlight>

Davrot@uni-bremen.de: /* Extensions */

2026-08-10T15:21:54Z

Extensions

← Older revision		Revision as of 15:21, 10 August 2026
Line 34:		Line 34:

	'''pi-hermes-memory''' — Gives Pi persistent memory across sessions: it remembers facts, corrections, and past failures, supports full-text search over old conversations ("what did we discuss about auth?"), and scans everything it stores for secrets before saving. Install it if you're tired of Pi forgetting everything each time you start a new session.		'''pi-hermes-memory''' — Gives Pi persistent memory across sessions: it remembers facts, corrections, and past failures, supports full-text search over old conversations ("what did we discuss about auth?"), and scans everything it stores for secrets before saving. Install it if you're tired of Pi forgetting everything each time you start a new session.

			=== Update extension ===
			<syntaxhighlight lang="bash">pi update --extensions</syntaxhighlight>

Davrot@uni-bremen.de: Created page with "== Basis tool == npm install -g @earendil-works/pi-coding-agent == Extensions == # Important!!! Go to your cd ~ if you use pi install !!! cd ~ pi install npm:pi-subagents pi install npm:pi-mcp-adapter pi install npm:@narumitw/pi-lsp pi install npm:pi-agent-browser-native pi install npm:pi-web-access pi install npm:pi-agent-extensions pi install npm:pi-codex-goal pi install npm:context-mode pi..."

2026-08-10T15:01:50Z

Created page with "== Basis tool == <syntaxhighlight lang="bash"> npm install -g @earendil-works/pi-coding-agent </syntaxhighlight> == Extensions == <syntaxhighlight lang="bash"># Important!!! Go to your cd ~ if you use pi install !!! cd ~ pi install npm:pi-subagents pi install npm:pi-mcp-adapter pi install npm:@narumitw/pi-lsp pi install npm:pi-agent-browser-native pi install npm:pi-web-access pi install npm:pi-agent-extensions pi install npm:pi-codex-goal pi install npm:context-mode pi..."

New page

== Basis tool ==
<syntaxhighlight lang="bash">
npm install -g @earendil-works/pi-coding-agent
</syntaxhighlight>

== Extensions ==
<syntaxhighlight lang="bash"># Important!!! Go to your cd ~ if you use pi install !!!
cd ~
pi install npm:pi-subagents
pi install npm:pi-mcp-adapter
pi install npm:@narumitw/pi-lsp
pi install npm:pi-agent-browser-native
pi install npm:pi-web-access
pi install npm:pi-agent-extensions
pi install npm:pi-codex-goal
pi install npm:context-mode
pi install npm:pi-hermes-memory</syntaxhighlight>Claude says:

'''pi-subagents''' — Lets Pi delegate work to focused child agents instead of doing everything in one long context. It ships ready-made roles (scout, researcher, worker, reviewer, oracle) that run in isolated sessions, in the foreground or background, and can be steered mid-run. Install it if you want a "second set of eyes" for code review, research, or parallel work without polluting your main conversation.

'''pi-mcp-adapter''' — Connects Pi to MCP (Model Context Protocol) servers through a single proxy tool instead of registering every individual tool up front, which normally costs 10,000+ tokens per server. Install it if you want to use MCP servers (browsers, databases, search APIs, etc.) with Pi without burning through your context window.

'''@narumitw/pi-lsp''' — Wires real language servers into Pi so it gets actual diagnostics and code actions (not just guesses) across languages like TypeScript, Python, Rust, Go, and more. Install it if you want Pi's edits checked against a genuine compiler/linter instead of relying purely on the model's judgment.

'''pi-agent-browser-native''' — Exposes browser automation as a native Pi tool (built on the <code>agent-browser</code> project), so the agent can open pages, click around, and inspect results directly instead of shelling out through bash. Install it if your workflows involve interacting with live web pages or web apps.

'''pi-web-access''' — Gives Pi web search, URL fetching, GitHub repo cloning, PDF extraction, and YouTube/video understanding, with support for many search providers (Brave, Tavily, Kagi, self-hosted SearXNG, etc.). Install it if you want Pi to research things on the open web as part of its normal workflow.

'''pi-agent-extensions''' — A bundle of 17 smaller extensions and themes in one install: session search, structured question-asking, session hand-offs, a status footer, review tooling, and more. Install it as a convenient "starter pack" instead of hunting down and installing each small quality-of-life extension separately.

'''pi-codex-goal''' — Adds Codex-style goal tracking: a <code>/goal</code> command plus tools so Pi can track a long-running objective, verify completion, and resume it correctly after a session is reloaded or forked. Install it for long or multi-step tasks where you want the agent to stay anchored to a single, verifiable objective instead of drifting.

'''context-mode''' — A context-window optimizer that sandboxes heavy tool output (bash logs, search results, etc.) to files instead of dumping it all into the conversation, cutting context usage substantially, and also persists session memory and enforces consistent tool-output routing. Install it if your Pi sessions are running out of context quickly due to verbose tool output.

'''pi-hermes-memory''' — Gives Pi persistent memory across sessions: it remembers facts, corrections, and past failures, supports full-text search over old conversations ("what did we discuss about auth?"), and scans everything it stores for secrets before saving. Install it if you're tired of Pi forgetting everything each time you start a new session.