Open-source design agent: on-brand stills, decks, diagrams, charts and motion graphics from a chat thread, built on Deep Agents.
Official engineering sources
Check the relevant primary source before changing an external contract. These APIs move weekly; installed package behavior and a live probe outrank model memory and this list. Update the owning architecture page when supported behavior changes.
Deep Agents and Managed Deep Agents
- Deep Agents (OSS): https://github.com/langchain-ai/deepagents · docs https://docs.langchain.com/oss/python/deepagents/overview
- Deep Agents customization, subagents, skills, backends, human-in-the-loop:
https://docs.langchain.com/oss/python/deepagents/customization,
https://docs.langchain.com/oss/python/deepagents/human-in-the-loop
All MDA pages share the prefix
https://docs.langchain.com/langsmith/python/managed-deep-agents-:
| Topic | Page suffixes |
|---|---|
| Start | overview, quickstart, project-structure, migrate |
| Agent definition | agent-definition, instructions, skills, tools, middleware, runtime |
| Integrations | search, connections, mcp-connectors, mcp-endpoint |
| State and environment | memory, sandboxes, context-hub |
| Identity and schedules | identity, schedules |
| Channels | channels, channels-slack, channels-http, agent-owned-interrupts |
| Develop and ship | local-development, tutorial, deploy, cli, evals |
- Public landing repository and changelog: https://github.com/langchain-ai/managed-deepagents
- Coding-agent skills for Deep Agents and MDA projects, vendored into
.agents/skills/at the commit inskills-lock.json: https://github.com/langchain-ai/langchain-skills - LangSmith skills (tracing, datasets, evaluators), vendored the same way:
https://github.com/langchain-ai/langsmith-skills · trace queries use the Python SDK's
Client.list_runs(https://docs.smith.langchain.com/reference/python/client) - LangSmith sandboxes: https://docs.langchain.com/langsmith/sandboxes · regions: https://docs.langchain.com/langsmith/regions-faq · pricing: https://www.langchain.com/pricing
- PyPI: https://pypi.org/project/managed-deepagents/ (0.9.4 stable on 2026-10-20;
0.10.0.devNbuilds are cut from feature branches, never pin them) · https://pypi.org/project/deepagents/ (0.7.28) - SDK source is private to LangChain staff (
langchain-ai/managed-deepagents-sdk; its examples directory holds the MIT-licensed lineage of the internal agent). Builders with access may read it for current behavior, but the public repository depends only on the published package and public docs.
Known doc drift as of 2026-10-17 (trust the installed package): the SDK README still shows
scope: "agent" sandboxes (rejected at runtime); the migrate page shows define_memory(scope="agent")
(raises in 0.9.3; use define_memory(agent=MemoryLayer())); the PyPI README says Python 3.9+ (3.11+
is required). Declaring a sandbox clears permissions; schedules require identity.py.
Verified against the installed 0.9.3 package while building (its README ships in
managed_deepagents-0.9.3.dist-info/METADATA): mda build reads declarations statically, so
sandbox/__init__.py and schedules/*.py hold literals or top-level constants; a static agent
declares MCP servers in tools/mcp.py as a module-level mcp (passing mcp= to
define_deep_agent is refused); an agent factory may select mcp, memory and the other managed
resources per run (0.9.4), keeps the project's declaration for any it leaves out, and cannot give a
selected memory layer the allow(context) policy (deprecated in 0.9.0); connector tools are named
{server}_{tool}; schedule delivery is an after_agent hook installed ahead of authored middleware.
Confirm each URL still resolves when you move a pin forward; the docs site renames pages.
HyperFrames (HeyGen) — video engine
- Site: https://hyperframes.heygen.com · Quickstart: https://hyperframes.heygen.com/quickstart
- Catalog: https://hyperframes.heygen.com/catalog
- Repository (Apache-2.0): https://github.com/heygen-com/hyperframes · releases
https://github.com/heygen-com/hyperframes/releases · adopters list
ADOPTERS.md - Agent skills:
npx skills add heygen-com/hyperframes(standalone) or the HyperFrames plugin; update withnpx hyperframes skills update. - CLI at the pinned 0.8.169 (verified with
--helpin the sandbox):hyperframes init | lint | check | snapshot | preview | render --quality draft|looks|delivery --output <file>;validate,inspectandlayoutare deprecated aliases ofcheck. - Studio (desktop preview app): https://hyperframes.dev/studio/download
Paper — shared design canvas
- MCP docs: https://paper.design/docs/mcp
- Downloads (Paper Desktop): https://paper.design/downloads
- Agent plugins:
claude plugin marketplace add paper-design/agent-plugins && claude plugin install paper-desktop@paper; Codex:codex mcp add paper -- /path/to/paper mcp. - Transport: Paper Desktop starts the MCP server and installs the
paperCLI. The recommended transport is the stdio serverpaper mcp; the legacy HTTP endpointhttp://127.0.0.1:29979/mcpis served only while a file is open. No hosted or token-based remote MCP is documented as of this writing; free plans have MCP limits that reset on Pro.
Models and tool disclosure
- LangChain prebuilt middleware (tool search, LLM tool selector, summarization, context editing): https://docs.langchain.com/oss/python/langchain/middleware/built-in
- Anthropic tool search: https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool
- Anthropic context editing and compaction: https://platform.claude.com/docs/en/build-with-claude/context-editing
- Anthropic vision (image token cost): https://platform.claude.com/docs/en/build-with-claude/vision
- OpenAI tool search: https://developers.openai.com/api/docs/guides/tools-tool-search
- OpenAI image generation: https://developers.openai.com/api/docs/guides/image-generation
Media services (optional)
- ElevenLabs text to speech and music: https://elevenlabs.io/docs
- FFmpeg: https://ffmpeg.org/documentation.html
- Chrome Headless Shell: https://developer.chrome.com/blog/chrome-headless-shell
- sharp: https://sharp.pixelplumbing.com
- Apache ECharts: https://echarts.apache.org · D2: https://d2lang.com
Slack
- Slack agents and AI apps (streaming, status): https://docs.slack.dev/ai/
- Bolt for Python: https://docs.slack.dev/tools/bolt-python/
- Socket Mode: https://docs.slack.dev/apis/events-api/using-socket-mode
Skills format
- Agent Skills specification: https://agentskills.io/specification