$ loading_
Encode states, predict rollouts, and plan goals in a 2D world model.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Oneiros MCP Server" yet — see the docs or source repo.
Use the Oneiros MCP Server: first encode this 2D point-mass observation, then predict the future rollout for the action sequence [right, right, up, up], and return the latent state and position-change summary for each step.
Returns the encoded state plus a step-by-step predicted rollout, state changes, and a brief explanation.
Use the Oneiros MCP Server to encode the current observation and generate an executable action plan to reach target coordinate (8, 6) in the 2D environment; also report the estimated number of steps and direction of progress at each step.
Returns an action sequence from the current state to the goal, the expected trajectory, and why the plan should reach the target.
Use the Oneiros MCP Server to encode the current observation, predict rollouts for Plan A and Plan B, compare their likelihood of reaching the target region, path length, and stability, and recommend the better option.
Returns a comparison of both predicted plans, key metric analysis, and a recommendation.
Convert planning documents into SQLite data and expose plan metadata to AI agents.
Orchestrate multi-model agents for plan-code-review-deliver workflows.
Delegate routine code-generation tasks to a local LLM and save frontier-model tokens.
Connect to Jupyter via MCP to run code and explore data interactively.
Break down complex tasks into steps and track plan progress efficiently.
Provides reasoning, coding, anti-deception, and memory harness MCP tools.