Skip to content
@basilisk-labs

Basilisk Labs

Basilisk Labs is an R&D space for synthetic agency, emergent memory, cognitive graphs, and coevolving human–AI infrastructures

Basilisk Labs

Infrastructure for long-range collaboration between people and autonomous agents.

Website AgentPlane Email

Git-native Agent work Audit trail Open source

Basilisk Labs builds tools for agentic software work that needs memory, coordination, and accountability over time. Our current center of gravity is AgentPlane: an open-source audit layer that turns coding-agent sessions into reviewable Git artifacts.

We are interested in systems where the important question is not just whether an agent produced a diff, but whether a human or another agent can reconstruct the task, plan, approval, verification, and closure chain later.

Focus

Area What we build
Agent coordination Repo-local workflows for planning, handoff, verification, and finish states.
Change evidence Agent Change Records, task artifacts, signed catalogs, and reviewable traces.
Developer tooling CLI-first tools that work with Codex, Claude Code, Cursor, Aider, and GitHub Actions.
Long-lived memory Practices and infrastructure that preserve useful context without depending on chat history.

Projects

Project Status Description
agentplane Open source Audit layer for coding agents. Keeps task, plan, verification, and closure evidence in Git.
agent-change-record Open standard JSON schema and tooling for machine-readable evidence manifests for agent-authored changes.
agentplane-recipes Catalog Signed recipes for reusable AgentPlane workflows and development practices.
setup-agentplane CI GitHub Action for installing AgentPlane inside CI runners.
homebrew-tap Distribution Homebrew tap for AgentPlane CLI releases.
scoop-bucket Distribution Scoop manifests for AgentPlane on Windows.
agentplane-harbor-adapter Experimental Benchmark adapter for evaluating AgentPlane as a control-plane wrapper around coding agents.
agentplane-marketing Knowledge base Public positioning, editorial, launch, and market-practice source documents for AgentPlane.

Principles

  • Keep workflow evidence close to the code.
  • Prefer explicit plans and verification over invisible agent state.
  • Make artifacts useful to both humans and machines.
  • Treat benchmarks, recipes, and integrations as evidence surfaces, not just growth assets.
  • Build small, inspectable tools before adding hosted complexity.

Start here

npm i -g agentplane
agentplane init
agentplane quickstart

Read the docs at agentplane.org or start from the AgentPlane repository.

Contact

Pinned Loading

  1. agentplane agentplane Public

    🛩️ Git-native workflow control for coding agents: approved plans, verification, and reviewable evidence for Claude Code, Codex, Cursor, and Aider.

    TypeScript 48 6

  2. agent-change-record agent-change-record Public

    🧾 Agent Change Record: a Git-native evidence manifest standard for reviewing AI-authored software changes.

    JavaScript

  3. agentplane-recipes agentplane-recipes Public

    📚 Signed AgentPlane recipe catalog for reusable AI coding workflows, repo-local practices, and development playbooks.

    TypeScript 1

  4. agentplane-blueprints agentplane-blueprints Public

    🧭 Installable AgentPlane blueprint catalog for reusable coding-agent workflows, verification routes, and task execution patterns.

    JavaScript

  5. openclaw-deus openclaw-deus Public

    🧪 Experimental OpenClaw automation workspace for local agent workflow research and prototypes.

    JavaScript 1 1

Repositories

Showing 10 of 11 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…