Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.
The English summary is being prepared. Showing the original description.
Operate the Bindu agent microservice framework: Python bindufy agents, A2A protocol, security, gRPC SDKs, deployment, Gateway, and Inbox.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Use this skill when a task is about building, running, integrating, or troubleshooting Bindu: a Python-first framework that turns AI handlers into DID-identified A2A-speaking microservices, with optional Hydra auth, DID signatures, mTLS, x402 payments, gRPC language SDKs, boxd runtime deployment, a Gateway planner, and an operator Inbox UI.
Install the public package in the target environment when needed:
python -m pip install bindu
When a user is working with an installed Bindu package, first confirm the package and CLI surface without starting a server:
python scripts/check_bindu_install.py --json
If the user is editing a Bindu checkout, run project-native commands only after reading the relevant sub-skill and respecting repo maintenance rules in references/repo-maintenance.md.
| User intent | Read |
|---|---|
Write a Python agent, call bindufy(), validate config/handler shape, send A2A JSON-RPC, poll tasks, expose public skills, or interpret negotiation | sub-skills/agent-authoring-and-a2a/SKILL.md |
| Configure or debug Hydra OAuth, DID keys/signatures, private skill catalogs, mTLS, x402 payments, payment sessions, or auth/payment errors | sub-skills/security-identity-and-payments/SKILL.md |
Register TypeScript or other language agents, debug core :3774, callback gRPC, proto drift, generated stubs, or SDK heartbeat/handler responses | sub-skills/grpc-and-language-sdks/SKILL.md |
Use bindu serve, bindu deploy, runtime-boxd, source packaging, secret exclusion, storage/scheduler, migrations, observability, tunneling, or maintainer commands | sub-skills/deployment-runtime-and-operations/SKILL.md |
Operate Bindu Gateway /plan, recipes, peer catalogs/auth, send-and-poll orchestration, Inbox UI, personal agent, contacts, demo peers, or webhooks | sub-skills/gateway-inbox-and-orchestration/SKILL.md |
references/capability-map.md maps Bindu features to sub-skills, bundled references, and verification evidence.references/troubleshooting.md covers cross-cutting install/import, generated-code, port, optional-service, and routing problems.references/repo-maintenance.md summarizes repository contribution rules, native commands, and generated-code boundaries.references/repo-provenance.md records the source snapshot and evidence paths used to create this skill.references/repo-routing-metadata.json is structured router metadata for managed repo-skill import tooling.scripts/check_bindu_install.py verifies the installed distribution, important imports, CLI entry point, and optional environment signals. It does not start servers, contact networks, read secrets, or require the original repository checkout.proto/agent_handler.proto in a checkout and regenerate with the documented commands..env, key, wallet, cert, or token files. Use .env.example with allowlist pragmas only when the repo's secret scanner requires it.app_settings for Bindu config and get_logger(__name__) for logging when editing the repository.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.
The English summary is being prepared. Showing the original description.
Guide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.
The English summary is being prepared. Showing the original description.
Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.
The English summary is being prepared. Showing the original description.
Operate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.
The English summary is being prepared. Showing the original description.
Use Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model inference/offload, checkpointing, tracking, and troubleshooting.
The English summary is being prepared. Showing the original description.
Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.
The English summary is being prepared. Showing the original description.