Agent Switchboard

LLM Space

by DeerFlow

Prototypes, traces, replays, and evaluates LLM agents in a local macOS desktop app, and exports threads as runnable LangGraph agents, for agent builders.

Keep it with up to 9 other tools you're setting up, then share them all as one link.

Compare

Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.

Access
Not listed
Auth
API Key
Skills
4

Skills

  • Agent Run Tracing

    Shows every model call and tool run inside the agent loop as it happens.

  • Replay Debugging

    Replays a run from history and steps through it to locate failures.

  • Agent Evaluation

    Measures agent performance across runs.

  • LangGraph Project Generation

    Turns a thread into a runnable LangGraph agent project.

Code & DevToolsOrchestrationagent-debuggingtracingprompt-engineeringevaluationdesktop-appmacoslanggraphmcp-client
Visit Agent
llm-space
Prototypes, traces, replays, and evaluates LLM agents in a local macOS desktop app, and exports threads as runnable LangGraph agents, for agent builders.
fields
nameLLM Space
providerDeerFlow
urlhttps://deer-flow.github.io/llm-space/
categoriescode-devtools · orchestration
access—
authapiKey
streamingfalse
pushfalse
verifiedfalse
officialfalse
sponsoredfalse
tagsagent-debugging, tracing, prompt-engineering, evaluation, desktop-app, macos, langgraph, mcp-client
skills
agent-tracingAgent Run TracingShows every model call and tool run inside the agent lo…
replay-debuggingReplay DebuggingReplays a run from history and steps through it to loca…
agent-evaluationAgent EvaluationMeasures agent performance across runs.
langgraph-exportLangGraph Project GenerationTurns a thread into a runnable LangGraph agent project.