Tag

oh-my-pi

Terminal-native AI coding agent that performs hash-anchored file edits, LSP-powered code intelligence, an IPython kernel, and orchestrated subagents—designed for in-terminal development workflows with reproducible, fine-grained code changes.

obsidian-skills

Provides a set of Agent Skills that let LLM agents read, edit, and manipulate Obsidian files (Markdown, Bases, JSON Canvas) and interact with Obsidian via the CLI. Implements the Agent Skills spec for use with Claude Code, Codex CLI, and OpenCode, enabling automated note workflows and RAG over an Obsidian vault.

Planning with Files

Implements a Manus-style, file-backed planning workflow for AI agents using a three-file Markdown pattern (task_plan.md, findings.md, progress.md) to persist plans, findings and session logs—reducing context drift and enabling session recovery. Adds IDE/CLI hooks to re-read plans and verify completion.

Hister

Indexes full text of visited web pages and local files on a self‑hosted server so you can search your personal knowledge from a web UI, terminal, CLI, or an AI assistant. Runs without mandatory telemetry, offers a browser extension for automatic capture, and supports optional semantic search via a configurable embeddings endpoint.

9Router

Routes CLI coding-tool requests to many AI providers with built-in tool-output compression (saves ~20–40% tokens), real-time quota tracking, and automatic subscription→cheap→free fallback for zero-downtime coding.

jcode

Terminal-first coding agent harness for multi-session LLM workflows, offering session memory, provider integrations, browser automation, and swarm collaboration. Tuned for low RAM and very fast startup to support many concurrent sessions.

UI Skills

Provides a set of versioned "skills" that codify UI design standards and automated checks for design engineers and AI agents. Includes a CLI to discover, install, and run skills like baseline UI rules, accessibility fixes, motion-performance tuning, and metadata corrections.

Destructive Command Guard (dcg)

Intercepts and blocks destructive git, filesystem and CLI commands before they execute when run by AI coding agents. Offers sub-millisecond hook latency, 50+ modular rule packs, heredoc/inline-script AST scanning, agent-specific integrations and configurable bypass/allow-once workflows.

Ralph

Runs an autonomous agent loop that uses AI coding tools (Amp or Claude Code) to implement PRD user stories iteratively, persisting context via git history, progress.txt and prd.json; designed for small, CI-backed tasks.

Hyper-Extract

Transforms unstructured documents into strongly-typed Knowledge Abstracts with one CLI command, extracting entities and relations into graphs, hypergraphs, and spatio‑temporal structures. Includes 80+ templates, multiple RAG engines, local vLLM support, Obsidian export and an MCP server.

Headroom

Compresses any context sent to LLMs (tool outputs, DB reads, RAG results, files, logs) to cut tokens by ~70–95% while preserving reversible originals; runs as a proxy or Python/TypeScript SDK with integrations for common agent frameworks.

pi-subagents

Enables Pi to delegate tasks to focused child agents for code review, parallel audits, background jobs, and saved workflows. Supports foreground and background runs, session artifacts, worktree isolation, and built-in role agents to simplify orchestration.