Skip to content

Repository files navigation

AgentSeek

Discover · Create · Run · Observe · Iterate

GitHub stars GitHub release PyPI version Python versions Build status
Contributors Open issues License Documentation

Template-first tooling for editable local agent applications and their complete development lifecycle.

English · 中文

Experience the local ADLC · What is AgentSeek? · Lifecycle · Guided templates · Community

Development

Star AgentSeek to follow its progress.


AgentSeek is a template-first toolkit for local agent application development. It gives editable generated projects one predictable lifecycle: discover, create, inspect, configure, check, run, observe, and iterate.

AgentSeek 0.1.1 resolves lifecycle-v2 templates from the immutable agentseek-ai/agentseek-templates catalog. The CLI lists templates from its embedded registry snapshot and fetches named template content at the exact locked commit.

Experience the local ADLC

Start with the shipped deepagents/research walkthrough. It creates a fully editable DeepAgents research app with a native LangGraph backend and a React frontend as its primary user experience.

# Install the lifecycle CLI, then create and enter the generated project.
uv tool install agentseek
agentseek create deepagents/research --no-input
cd research_deepagent

# Inspect declared entry points before configuring local credentials.
agentseek info
cp .env.example .env
cp frontend/.env.example frontend/.env
$EDITOR .env

# Run the setup tasks declared by this project, then check readiness.
agentseek task --list
agentseek task sync
agentseek task frontend
agentseek doctor

# Preview the native commands, run the local stack, and check live services.
agentseek dev --dry-run
agentseek dev
# In another terminal, after agentseek dev starts, check live services.
agentseek doctor --live

The current scaffold declares only sync and frontend setup tasks. Its native backend resolves to uv run langgraph dev --port 2024 --no-browser, while the frontend resolves to npm run dev in frontend/.

For a one-off run, use uvx agentseek create deepagents/research --no-input instead of installing the CLI.

What is AgentSeek?

AgentSeek supplies the stable lifecycle surface around a generated project; it does not own that project's source, framework, runtime, or deployment. A template selects those pieces, and the generated project remains yours to edit.

AgentSeek architecture

The CLI connects people, coding agents, and desktop clients to a locked, versioned template catalog and an editable project lifecycle contract. The project then owns its runtimes and integrations, including models, tools, MCP servers, and external services.

Agent Development Lifecycle

The local ADLC keeps iteration anchored in the existing project instead of starting over: discover, create, inspect, configure, check, run, observe, and iterate back to inspect.

Agent development lifecycle

Stage Local command or project surface
Discover agentseek create --list-templates finds templates by goal.
Create agentseek create renders an editable project.
Inspect agentseek info shows its declared entry points and topology.
Configure .env and project configuration provide runtime credentials and choices.
Check agentseek doctor validates local readiness.
Run agentseek dev starts the template-owned local stack.
Observe agentseek doctor --live and lifecycle signals show its current state.
Iterate Change the generated project, then return to Inspect.

Observability throughout the loop

Lifecycle diagnostics answer whether the declared project is ready and running: agentseek info shows topology, agentseek doctor performs preflight checks, and agentseek doctor --live checks declared services after startup. For Desktop, scripts, and other machine consumers, use the versioned JSON contract instead of parsing human output.

agentseek info --json
agentseek doctor --json
agentseek doctor --live --json
AGENTSEEK_CONSOLE=true agentseek doctor --live

info --json contains normalized services, references, and safe actions such as which URL can be opened directly. It never includes environment values or raw process or task commands. AGENTSEEK_CONSOLE=true enables local CLI spans and lifecycle events. Optional LangSmith tracing, configured through the settings already present in deepagents/research, answers what the agent did inside an individual run. When your LangSmith API key belongs to the APAC or another non-default region, set LANGSMITH_ENDPOINT explicitly (for example https://apac.api.smith.langchain.com); otherwise traces may fail to upload to the cloud. See the observability and tracing guide for setup and troubleshooting.

Guided templates

Choose by goal, then inspect a specific template before creating it. AgentSeek maintains many templates without requiring you to memorize a catalog dump.

agentseek create --list-templates
agentseek create --list-templates --filter deepagents
agentseek create deepagents/research --describe

Core concepts and commands

Concept What it provides
Template A complete, editable application scaffold with its chosen runtime.
Lifecycle file The project-owned declaration of paths, environment checks, services, processes, and tasks.
AgentSeek CLI A consistent local interface for the declared lifecycle.
Command Purpose
create Render an application template.
info Show declared entry points and lifecycle metadata.
task Run a project-defined setup task.
doctor Check local readiness or live declared-service health.
dev Run the local development stack.

Documentation

🌐 Next Steps & Community

Explore Deep Agents in Action, a free LangChain / DeepAgents course with AgentSeek labs, in the course repository. Read the documentation, join GitHub Discussions, browse or report an issue, or follow the contribution guide.

GitHub Discussions Contribute to AgentSeek

🛠️ Development

git clone https://github.com/ob-labs/agentseek.git
cd agentseek
make install
make check
make test
make docs-test

Contributing

Contributions, fixes, and template improvements are welcome.

AgentSeek contributors

📄 License

Apache-2.0

About

AgentSeek is an application development lifecycle toolkit for AI ecosystem apps, built by OceanBase OSS Team.

Topics

Resources

Contributing

Stars

159 stars

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages