pi-agent-observer
Prompt-neutral runtime observability for pi agents
6.2k listings for pi · 0 reviewed by us
445 results · page 6 of 10
Prompt-neutral runtime observability for pi agents
RFC 2119 keyword normalizer extension for the Pi coding agent.
Local prompt counters for the Pi coding agent.
A customized fork of pi-open-tui for personal use. A polished TUI for Pi coding agent with an animated logo header, Starship-style footer, rounded editor, model metadata, and prompt-box user messages.
Inline session linter for Pi — flags vague openers, pronoun soup, scope creep, and other input anti-patterns above the editor.
pi extension that reads zed's open files and selected lines and injects them into prompts.
Pi extension: model + thinking + tools + system-prompt presets, with a UI on top.
Pi extension that strips global AGENTS.md and CLAUDE.md from the effective prompt for selected projects.
PI extension that auto-loads path-scoped rule files from .pi/rules and .claude/rules
Model Context Protocol (MCP) integration for pi-coding-agent. Connect to any MCP server (stdio, SSE, StreamableHTTP, WebSocket) and use its tools, resources, and prompts natively.
Semantic token compression for pi terminal — filters noisy bash output and retroactively masks stale tool results in conversation history (per JetBrains Dec 2025 + Anthropic tool-result clearing)
OPPi Pi package: extensions, skills, prompts, and themes.
Pi extension for named presets that can set model, thinking level, tools, and per-preset system prompt instructions.
A personal stash of reusable prompt fragments for the Pi coding agent. Push prompts you think of mid-task, then pop them into the editor when you need them.
Pi coding-agent extension that adds a /loop command — run a prompt repeatedly with convergence detection, rich stop conditions, lifecycle hooks, a live TUI panel, and desktop notifications.
Production-grade Langfuse observability for Pi. Tracks prompts, turns, tools, and streaming assistant responses with native trace hierarchies, token usage, and cost monitoring.
Reusable pi package for company workflows
Intent-aware prompt rewriter and execution-contract compiler for Pi
Compatibility package renamed to @codella/pi-prompt-plan.
Custom compaction for pi — swap the model, template, and trigger for context compaction
Pi-native agent kit: extensions, skills, themes, prompts, and agents for pi-coding-agent
Intelligent model routing and prompt compression for Pi/Kiro
Pi skill + prompt + agents for shipping multi-feature work autonomously: decompose a design.md into a DAG of small features, each on its own git worktree+branch off a long-lived epic branch, squash-merged back, then opened as a single PR. Halt only when t
Goal mode extension for pi: persistent long-running objectives, /goal-set drafting, Sisyphus prompt style, autoContinue, and an above-editor status overlay. Fork with merged PR fixes for runtime init error and checkpoint delegation.
Pi extension that injects project context into first-turn prompts and compaction continuity messages.
Developer toolkit for Pi — modular skills for authoring extensions, skills, prompt templates, themes, packages, and context files. Includes introspection tools for version, docs, changelog, benchmarking, and loaded tools.
Pi extensions that shim Claude Code's tool API, letting agents, skills, and prompts built for Claude Code run in pi without modification.
Terminal AI agent for Stellar. Chat-driven payments, path payments, trustlines, and friendbot funding on testnet, with a separate signer daemon that prompts for explicit approval on every signature.
Pi package for per-session prompt stash history with alt+s stash/restore workflow.
GPT-5.6, Codex and Pi prompt-caching skill.
Open the last assistant message in your editor and sync edits back into the prompt
Pi extension: resolve @filepath (files & directories) in AGENTS.md, inject into system prompt
Review prompts before sending them to the main pi session.
A skill that teaches an LLM how to set up and/or use npm trusted publishing (OIDC) with GitHub Actions. No long-lived tokens, no 2FA prompts, no manual rotation.
Audit Pi system prompt, tool schema, context usage, and MCP overhead.
Cleepi git conventions: conventional-commit + branch-naming + PR-shape skills, with /commit and /pr prompts. Monorepo-aware domain and ticket-id resolution. Subject-line-only commits; no body, no footers, no Co-authored-by ever. Small modular PRs; title d
OS-level sandboxing for pi with interactive permission prompts (fork)
Pi extension that adds /agent prompt profile switching.
Standalone, configurable idea-capture extension for Pi: an `idea` tool and `/ideas` browser backed by docs/ideas/<8hex>.md artifacts, with JSON-configurable work-menu actions, shortcuts, refine prompt, and command name.
Track skill, prompt-template, extension, and built-in tool usage in pi so you can prune unused resources and keep pi light.
Saves LLM provider request payloads to the project's .pi folder for per-project debugging
pi extension for loading extra context files into the system prompt.
Role-based session configuration for pi coding agent. Launch a session as a named role and hot-swap roles mid-session, with optional pi-intercom and pi-mcp-adapter integration.
Periodic health check extension for pi — runs a heartbeat prompt as an isolated subprocess
A pi extension that adapts the system prompt per model/mode.
Pi package that translates user prompts to English and translates final assistant replies back to a configured language.
Council deliberation plugin for Pi with roster templates, personas, audit records, and council workflow prompts
Pi extension for designing loops that prompt coding agents.