agentera/agently-langchain-langgraph-translation
auto_agent/docs/skills/agently-langchain-langgraph-translation/SKILL.md
Translate LangChain/LangGraph patterns into Agently code (model control + TriggerFlow).
$ install --global
skillsauthnpx skillsauth add agentera/agently-nexustodo agently-langchain-langgraph-translationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Mar 28, 2026, 1:46 PM36.2s5 files scanned
SKILL.md
- name:
- agently-langchain-langgraph-translation
- description:
- Translate LangChain/LangGraph patterns into Agently code (model control + TriggerFlow).
LangChain/LangGraph -> Agently Translation Skill
Use this skill to translate LangChain/LangGraph code into Agently patterns for production services.
Core mapping (high level)
- PromptTemplate ->
agent.set_agent_prompt/agent.set_request_promptwith mappings - LLMChain ->
agent.input(...).output(...).start() - OutputParser -> Output Format +
get_data()/ensure_keys - Tools ->
@agent.tool_func+agent.use_tool(...) - Memory -> keep key memory (runtime_data or custom memory); avoid full history
- LangGraph node -> TriggerFlow chunk
- LangGraph edges/conditions -> TriggerFlow
when()/to()/if_condition()/match() - Streaming ->
get_generator/get_async_generatoror runtime_stream
Translation steps
- Identify data contracts (inputs/outputs) and enforce with Output Format.
- Convert graph nodes into TriggerFlow chunks.
- Replace edges with when/to/condition/collect.
- Convert tools to
@agent.tool_funcand call viause_toolor ReAct loop. - Use runtime_data for per-run state; keep only key memory.
References
references/overview.mdexamples/langchain_to_agently_map.pyexamples/langgraph_to_agently_triggerflow.py
Examples
See examples/run.sh for runnable commands.
Related Skills
agentera/agently-triggerflow-orchestration
data-ai
VerifiedTrustedCommunity
Event-driven TriggerFlow orchestration patterns and branching.
3SKILL.mdUpdated Mar 27, 2026
agentera/agently-streaming-and-react
tools
VerifiedTrustedCommunity
Streaming outputs, runtime streams, and ReAct-style tool loops.
3SKILL.mdUpdated Mar 27, 2026
agentera/agently-output-control
data-ai
VerifiedTrustedCommunity
Structured output patterns with ensure_keys, ordering, and instant streaming.
3SKILL.mdUpdated Mar 27, 2026
agentera/agently-fastapi-service
development
VerifiedTrustedCommunity
FastAPI service wrappers for Agently Agent + TriggerFlow (POST, SSE, WebSocket).
3SKILL.mdUpdated Mar 27, 2026