graph-robots

graph-robots/graph-as-policy

Plugin Claude Code

Plugin marketplace listing 2 plugins: gap, open-robot-skills.

graph-robots/graph-as-policy

Plugin Claude Code

Search robot skill registries, check robot/tool capabilities, and program, run, and debug verified robot task graphs (sim-first, safety-gated real) with the gap engine.

graph-robots/graph-as-policy

Skill Claude CodeCodex

Program robots with GaP (graph-as-policy) — compile natural-language tasks into typed, verified robot skill graphs and run them on simulators or real robots. Use when the user mentions GaP or graph-as-policy, robot manipulation, robot skills, robot tools or capabilities, skill registries, open-robot-skills, LIBERO or…

graph-robots/graph-as-policy

Agent

GaP is built to be driven by coding agents, not just humans. The engine repo ships an agent skill — a plain-markdown playbook (agent/skills/gap/SKILL.md) plus five reference deep-dives — that teaches an agent to search skill registries, check capabilities, run graphs in sim, generate and hand-author graphs, create…

graph-robots/graph-as-policy

Skill Claude CodeCodex

Produce a greeting for a named entity via a canonical script and a bundled prompt template. Use when a loader test needs a minimal skill bundle with scripts and prompts.

graph-robots/graph-as-policy

Skill Claude CodeCodex

Echo strings back from an in-process fixture model. Use when a loader test needs a minimal tool bundle with a tools.py.

graph-robots/open-robot-skills

Plugin Claude Code

Plugin marketplace listing 1 plugin: open-robot-skills.

graph-robots/open-robot-skills

Skill Claude CodeCodex

Run the MolmoAct LIBERO checkpoint (allenai/MolmoAct-7B-D-LIBERO-0812) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSCPOSE action space from agentview + wrist cameras, served behind a vLLM-style script speaking the openpi websocket…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Run the openpi π0.5 LIBERO checkpoint (pi05libero) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSCPOSE action space from agentview + wrist cameras; the policy server is the bundle's own preset (no policyid). Reads the graph-scoped…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Direct IK align-then-descend grasping. The gripper pre-rotates to the grasp orientation at a safe height ABOVE the target before descending straight down, avoiding the twist-while-closing failure mode of a blended rotate+descend. Use when no trajectory planner (curobo) is deployed or the scene is uncluttered enough…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Deterministic short-axis-aligned grasp with CuRobo. The grasp pose is computed geometrically (NOT sampled/scored) — the gripper approaches straight down with its finger-opening axis locked to the OBB's SHORTER horizontal axis, so the jaws close ACROSS the narrow dimension of an elongated target. Use for pan/pot…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Top-down grasping via a fast axis-locked linear descend with a collision-aware cuRobo fallback. A single graspdescendlinear node rises, translates over the target, and descends straight down (Z-locked, orientation held) onto the object; if the straight-line solve is infeasible (far-edge reach, no IK for the fixed…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Loop-head perception for pack-all / clean-all-items tasks. From ONE observation it localizes BOTH the destination container (basket, bin, box) AND the next remaining target item, using the pairwise VLM crop tournament with a container-excluding description so the target is never confused with the basket, then makes a…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Hierarchical perception for subpart targeting. Detects a parent object first (DINO+VLM), crops the camera image to the parent's bounding box, then detects and segments the named subpart inside the crop (DINO + SAM3), and uncrops + fuses depth to a world-frame OBB/mask/cloud — plus the parent object's OBB and cloud for…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Lightweight one-shot 3D object perception. Runs Grounding-DINO broad detection, a SINGLE VLM set-of-marks letter pick over the labeled boxes, SAM3 box segmentation, depth back-projection, and geometry.filterandcomputeobb. No pairwise tournament, no multi-view safe-gate. Returns a clean notfound output (no exception)…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Fast single-path 3D object perception. Runs Grounding-DINO broad detection, a pairwise VLM crop tournament to identify the target box, SAM3 box segmentation, and depth back-projection to a world-frame point cloud, finished by geometry.filterandcomputeobb for a clean oriented bounding box, mask, and cloud. Multi-camera…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Long-running skill that drives the SAM3 tracker from the graph-scoped observation stream. Seeds the tracker via text prompt on the first frame, then polls the stream at updatehz and advances via sam3.trackerupdate until the workflow signals termination, publishing a tracker snapshot per tick. Use when a workflow needs…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Move the currently-held object to a destination and release. The gripper enters this subgraph holding the object; on exit the object has been placed. For a walled container (basket / bin / box / tote) the default is a straight-Z descent to inside the walls (transportdescendlinear → release); for placement ONTO a…

graph-robots/open-robot-skills

Skill Claude CodeCodex

NVIDIA cuRobo motion planning — collision-free trajectories to grasp goalsets, transport with an attached object, constrained linear moves, single-pose planning, geometric IK, batch grasp feasibility, and joint-trajectory collision validation. Use when a workflow needs GPU-accelerated, collision-aware arm motion plans.

graph-robots/open-robot-skills

Skill Claude CodeCodex

Open-vocabulary 2D object detection via the Gemini Robotics-ER API — one call returns pixel-space bounding boxes with labels and scores for a text query. Use when a workflow needs a detection box to seed segmentation (e.g. sam3.segmentbox) or coarse localization without any local GPU model.

graph-robots/open-robot-skills

Skill Claude CodeCodex

Pure-math 3D geometry toolbox — back-project masks and depth to point clouds, DBSCAN-filter noise, fit oriented bounding boxes, derive top-down/front grasp poses, and reconstruct collision worlds from RGB-D frames. Use when a workflow needs perception geometry or planner inputs computed on CPU with no model weights.

graph-robots/open-robot-skills

Skill Claude CodeCodex

Grounding DINO zero-shot object detection — natural-language queries to labeled 2D bounding boxes with confidence scores. Use when a workflow needs to locate named objects in an RGB image before segmenting or grasping them.

graph-robots/open-robot-skills

Skill Claude CodeCodex

Visual pointing and Q&A via the Molmo VLM served from a self-hosted vLLM endpoint (OpenAI-compatible API). Use when a workflow needs a single pixel coordinate for a named object (pointprompt) or Molmo-grade visual question answering and a vLLM server is available; for an API-only zero-GPU alternative use the gemini-er…

graph-robots/open-robot-skills

Skill Claude CodeCodex

Segment Anything 3 — text-, point-, and box-prompted instance segmentation, plus a stateful streaming video tracker that carries object identity through SAM3's memory bank. Use when a workflow needs open-vocabulary masks from an RGB image or needs to follow one object across frames.