Back to directory

AgentSeek

A template-first CLI toolkit for local AI agent application development, generating an editable starter project from a locked template catalog and giving it a consistent lifecycle of commands.

AgentSeek

AgentSeek is a command-line toolkit that generates editable, local AI agent application projects from a versioned, immutable catalog of templates, then gives each generated project a consistent lifecycle of commands: discover available templates by goal, create a project from one, inspect its declared entry points, configure it through environment variables and project settings, check local readiness, run it, observe its behavior, and iterate.

AgentSeek does not own a generated project's source code, framework, runtime, or deployment; a chosen template supplies those, and the resulting project belongs entirely to the user to edit going forward, including its models, tools, MCP servers, and external services. A bundled example template creates an editable research application with a LangGraph backend and a React frontend, runnable directly with a single command with no separate install step. The CLI resolves templates from an embedded registry snapshot and fetches the actual template content at an exact, locked commit for reproducibility.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.