langchain-ai/deepagents
The batteries-included agent harness.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http docs-langchain https://docs.langchain.com/mcp $ claude mcp add --transport http reference-langchain https://reference.langchain.com/mcp
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add --transport http docs-langchain https://docs.langchain.com/mcp $ claude mcp add --transport http reference-langchain https://reference.langchain.com/mcp
$ npx degit langchain-ai/deepagents/.agents/skills/textual-screenshot .claude/skills/textual-screenshot $ npx degit langchain-ai/deepagents/examples/content-builder-agent/skills/blog-post .claude/skills/blog-post $ npx degit langchain-ai/deepagents/examples/content-builder-agent/skills/social-media .claude/skills/social-media $ npx degit langchain-ai/deepagents/examples/deploy-coding-agent/skills/code-review .claude/skills/code-review $ npx degit langchain-ai/deepagents/examples/deploy-coding-agent/skills/coding-prefs .claude/skills/coding-prefs $ npx degit langchain-ai/deepagents/examples/deploy-coding-agent/skills/planning .claude/skills/planning $ npx degit langchain-ai/deepagents/examples/deploy-gtm-agent/skills/competitor-analysis .claude/skills/competitor-analysis $ npx degit langchain-ai/deepagents/examples/deploy-gtm-agent/subagents/market-researcher/skills/analyze-market .claude/skills/analyze-market $ npx degit langchain-ai/deepagents/examples/nvidia_deep_agent/skills/cudf-analytics .claude/skills/cudf-analytics $ npx degit langchain-ai/deepagents/examples/nvidia_deep_agent/skills/cuml-machine-learning .claude/skills/cuml-machine-learning $ npx degit langchain-ai/deepagents/examples/nvidia_deep_agent/skills/data-visualization .claude/skills/data-visualization $ npx degit langchain-ai/deepagents/examples/nvidia_deep_agent/skills/gpu-document-processing .claude/skills/gpu-document-processing $ npx degit langchain-ai/deepagents/examples/text-to-sql-agent/skills/query-writing .claude/skills/query-writing $ npx degit langchain-ai/deepagents/examples/text-to-sql-agent/skills/schema-exploration .claude/skills/schema-exploration $ npx degit langchain-ai/deepagents/libs/code/examples/skills/arxiv-search .claude/skills/arxiv-search $ npx degit langchain-<redacted>-docs .claude/skills/langgraph-docs $ npx degit langchain-ai/deepagents/libs/code/examples/skills/skill-creator .claude/skills/skill-creator $ npx degit langchain-ai/deepagents/libs/code/examples/skills/web-research .claude/skills/web-research $ npx degit langchain-ai/deepagents/libs/talon/deepagents_talon/defaults/skills/configuration-hardening .claude/skills/configuration-hardening $ npx degit langchain-ai/deepagents/libs/talon/deepagents_talon/defaults/skills/safety .claude/skills/safety
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (2)
| server | source | est. tokens |
|---|---|---|
| docs.langchain.com · "docs-langchain" | remote · remote | 2.5k |
| reference.langchain.com · "reference-langchain" | remote · remote | 2.5k |
Skills (20)
Similar rigs
byronxlg/skillfold
Declarative skill manager for Claude Code and Codex. Declare skills in YAML, pin exact revisions in a lockfile, install them reproducibly into .claude/skills.
Skill Collector 2.2k tok ·
kyegomez/swarms
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
Pragmatist 8.9k tok ·
Idun-Group/idun-agent-platform
🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip install. Self-hosted, no vendor lock-in.
Pragmatist 10.7k tok ·
pretend1111/claude-desktop-app
Desktop AI assistant powered by Claude API
Pragmatist 681 tok ·