deep-agents-core

Originally fromjackjin1997/clawforge
Installation
Summary

Foundation framework for building multi-step agents with built-in planning, memory, and skill delegation.

  • Provides six core middleware options: task planning, filesystem context management, subagent delegation, persistent memory, human approval workflows, and on-demand skill loading
  • Includes three always-present built-in tools: write_todos for task tracking, filesystem operations (ls, read_file, write_file, edit_file, glob, grep), and task for spawning specialized subagents
  • Supports two backend strategies: FilesystemBackend for local skill directories and StoreBackend for environments without filesystem access
  • Requires SKILL.md format with YAML frontmatter for skill discovery; skills load on-demand based on agent relevance rather than at startup
SKILL.md
  • Task Planning: TodoListMiddleware for breaking down complex tasks
  • Context Management: Filesystem tools with pluggable backends
  • Task Delegation: SubAgent middleware for spawning specialized agents
  • Long-term Memory: Persistent storage across threads via Store
  • Human-in-the-loop: Approval workflows for sensitive operations
  • Skills: On-demand loading of specialized capabilities

The agent harness provides these capabilities automatically - you configure, not implement.

Use Deep Agents When Use LangChain's create_agent When
Multi-step tasks requiring planning Simple, single-purpose tasks
Large context requiring file management Context fits in a single prompt
Related skills
Installs
6.1K
GitHub Stars
678
First Seen
Mar 3, 2026