Tag

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.

skills

Installs and manages reusable SKILL.md-based extensions for coding agents via a single npx CLI. Cross-agent support (40+ agents), flexible install scopes (project/global), and discovery rules make sharing and reusing agent behaviors simple.

GitHub Copilot SDK

Embeds Copilot's agentic workflows into applications via multi-language SDKs (TypeScript, Python, Go, .NET, Java, Rust). Uses the Copilot CLI runtime to handle planning, tool invocation, and file edits; supports BYOK and multiple auth methods.

AG Kit

Installs and manages a complete .agents workspace for Google Antigravity, providing agent engineering primitives—rules, skills, specialist agents, workflows, persistent memory, MCP guidance, orchestration, and a built-in PreToolUse safety hook for auditable, rollback-friendly agent workflows.

Accomplish

Automates file management, document creation, and browser workflows on your desktop by running a local Electron agent; you bring API keys or run local models, control folder access, and save repeatable 'skills' for approved, auditable automation.

CodeGraph

Pre-indexes a project's code into a local semantic knowledge graph that Claude Code can query—fewer tool calls and faster exploration with all data kept on-device. Features FTS5 search, call/impact analysis, auto-sync watcher, and multi-language support.

ECC

Provides an operator-grade system and reusable toolkit for building, running, and securing agentic workflows across multiple LLM harnesses — skills, hooks, memory, MCP integrations, and security scanning for production agent deployments.

Craft Agents

Desktop-first agent client that composes LLM-driven agents into document-centric, multi-session workflows; it wires APIs, MCPs and local tools into shareable sessions, supports multiple LLM providers, and exposes a headless server + CLI for automation.

agent-skills

A curated, security-first registry of verified, tested skills you can install into AI coding agents. Each skill is human-curated, scanned (Snyk/static analysis), and integrity-locked; delivered via a CLI and optional MCP server to multiple agents (Claude Code, Cursor, Copilot, etc.).

Craft Agents

Desktop + CLI agent-native client for managing multi-session conversations, connecting to multiple LLM providers and external data sources, and creating shareable agent skills and automations without editing code.

Meridian

Exposes the Claude Code SDK as a local Anthropic/OpenAI-compatible HTTP proxy so third-party tools can use Claude Max. Adds session management, streaming, multi-profile routing and OpenAI-format endpoints while respecting Anthropic's SDK auth, rate limits and prompt caching.