Multimodal Ai Python Packages

a11-kit

A streaming action runtime for AI agents, model serving, and multimodal APIs

federaide

P2P multi agent orchestration harness, universal automation system and IDE

federaide-dev-nightly

P2P multi agent orchestration harness, universal automation system and IDE

federate

P2P multi agent orchestration harness, universal automation system and IDE

supervertaler

Free, open-source standalone CAT tool: editor, AI translation, termbases, TMs, plus system-wide clipboard manager, SuperLookup, QuickTrans and voice dictation. See Supervertaler-for-Trados for the actively developed product.

vllm-mlx

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

termux-vision

🚀 The Sovereign On-Device Computer Vision & Multimodal VLM Inference Engine for Android Termux & ARM64 (Dual-Engine Python & Node.js/TypeScript)

humanbound

Open-source adversarial testing engine, SDK, and CLI for AI agents. Runs locally or against the Humanbound Platform.

kalibr

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

pomaidb

Embeded Vector Database for low performance devices

humanbound-firewall

Multi-tier firewall for AI agents — blocks prompt injections, jailbreaks, and scope violations. Local tiers first; LLM judge only when uncertain.

optimuskg

A modern multimodal knowledge graph with type-specific metadata across biomedical domains.

humanbound-cli

Open-source adversarial testing engine, SDK, and CLI for AI agents. Runs locally or against the Humanbound Platform.

evalrx

Autonomous failure investigation, root-cause analysis, and validated interventions for LLMs, VLMs, and agents.

aiandme

Multi-tier firewall for AI agents — blocks prompt injections, jailbreaks, and scope violations. Local tiers first; LLM judge only when uncertain.

vidchain

✅A Lightweight Video RAG Framework for Multimodal Reasoning

vidxp

VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.

llm-cost-optimizer

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

llm-cost-reduction

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

multimodal-auv

Leveraging Bayesian Neural Networks for multimodal AUV data fusion, enabling precise and uncertainty-aware mapping of underwater environments.

pop-persona

Persona layer protocol for stable, portable AI persona objects.

evalvitals

Autonomous failure investigation, root-cause analysis, and validated interventions for LLMs, VLMs, and agents.

hb-firewall

Multi-tier firewall for AI agents — blocks prompt injections, jailbreaks, and scope violations. Local tiers first; LLM judge only when uncertain.

sutra-sdk

Sovereign AI Initiative for Open Autonomous Cognitive Companion