neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
The archmax harness assembles one LangChain Deep Agent per workflow and governs every session with a declarative state machine you author in a single YAML file.
Developer toolsTypeScript · JavaScriptGitHub @archmax-aiOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Governed workflows for AI agents: a thin layer over LangChain Deep Agents that keeps an agent inside a declarative state machine, so it follows the business process and stays safe, compliant and auditable.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
A thin, governed layer over LangChain Deep
Agents. Every session runs
under a declarative workflow state machine you author in one YAML file.
Reliable automation with AI agents should follow the process, and the people who own that
process should be able to author it. Today that is out of reach for most domain experts.
Current automation tools fall short in three ways.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
A thin, governed layer over LangChain Deep
Agents. Every session runs
under a declarative workflow state machine you author in one YAML file.
Reliable automation with AI agents should follow the process, and the people who own that
process should be able to author it. Today that is out of reach for most domain experts.
Current automation tools fall short in three ways.Read the full README ↗