Ai Infrastructure Python Packages

tensorlake

Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications

hanzoai

Hanzo AI SDK for Python — the complete toolkit: agents, MCP tools, memory, inference, network, cloud, IAM/KMS. Hanzo's most complete SDK.

inkbox

SDK, skills, and examples for Inkbox: give AI agents a persistent identity with email, phone number, and internet address

awgraph

A semantic code graph for agents — AST + tree-sitter, call graphs.

awgit

Semantic version control on top of git — edit-ops and leases.

semantica

Graph-Native Infrastructure for Context and Accountable AI Systems

awrelay

Portable agent messaging — findings, alerts, coordination.

lium-io

Rent ready-to-use cloud GPUs in seconds. Lium CLI makes it easy to launch, manage, and scale GPU compute directly from your terminal. Fast, cost-optimized, and built for AI & ML developers.

awm

A portable, scoped agent memory.

distil-llm

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.

hanzo-mcp

Model Context Protocol server with 260+ tools for AI agents

modaic

Python SDK for Modaic

ferrogw

Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternative.

awshare

Publish an artifact and fetch it back verified.

dashclaw

Remote approvals, policy checks, and execution evidence for unattended AI agents.

awrecover

Labelled snapshots with an all-or-nothing restore.

hanzo-tools

Hanzo AI SDK for Python — the complete toolkit: agents, MCP tools, memory, inference, network, cloud, IAM/KMS. Hanzo's most complete SDK.

piqc

Free, read-only GPU waste scanner for Kubernetes inference clusters, by Paralleliq. Finds idle GPUs, oversized GPU tiers and wasted capacity in vLLM deployments.

awseal

Sign an artifact so a stranger can verify it.

tardigrade-db

Experimental LLM-native memory-kernel prototype for persistent agent memory in quantized KV-cache latent space.

ollama-herd

Local AI load balancer for Ollama and MLX fleets. Auto-discovery, smart routing, OpenAI-compatible API, zero config. Perfect for Mac Minis & Studios.

kalibr

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

modaic-client

Python SDK for Modaic

asap-protocol

Protocol for agent-to-agent communication with stateful orchestration, MCP-compatible and a public marketplace to discover and register agents.