Aws Bedrock Python Packages

toll-harness

Provider-neutral, self-hosted reference runtime for autonomous agents (Toll Bench harness).

agent-squad

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

agentegrity

The open standard for AI agent integrity. Evaluate, enforce, and prove that autonomous agents are adversarially coherent, environmentally portable, and verifiably assured.

cachellm-proxy

A drop-in semantic cache for LLM APIs. One proxy routes to OpenAI, Gemini, Groq, Claude, Ollama and Bedrock. 77% hit rate, 78% lower cost, zero wrong answers on new questions.

banko-ai-assistant

Agentic AI banking assistant with LangGraph multi-agent workflows, CockroachDB vector search, durable checkpointing, receipt OCR, fraud detection, and multi-provider support (IBM watsonx, OpenAI, AWS Bedrock, Google Gemini)

multi-agent-orchestrator

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

coverup

Automatic AI-powered test suite generator

agentforge-oss

Open-source multi-agent orchestration with cost-awareness, security, and compliance built in. Anthropic, OpenAI, and offline providers.

bedrock-quota

A CLI-based dashboard to see your AWS Bedrock model quotas and usage.

cognisn-spark

Secure Personal AI Research Kit — Multi-provider LLM web interface with MCP tools, voice chat, persistent memory, and autonomous actions

llm-token-guard

Track LLM token usage, enforce rate limit & budget policies, and trigger alerts across OpenAI, Groq, OpenRouter, and AWS Bedrock.

reviewcerberus

AI-powered code review tool that analyzes git branch differences and generates comprehensive review reports. Supports AWS Bedrock and Anthropic API. Features automated analysis of logic, security, performance, and code quality with smart token efficiency through prompt caching.

arxiv-atlas-mcp

Autonomous multi-agent system that maps new AI research from arXiv into a live semantic graph - with a CI-gated LLM evaluation harness, cost-guarded AWS Bedrock inference, and a public status dashboard.

llm-pdf-chunker

LLM-friendly PDF splitter & image optimizer. Chunk PDFs by size and downsample images for RAG/Bedrock.

guardrailprobe

Stop testing your model. Test your guardrail layer. guardrailprobe fires 78 OWASP LLM Top 10 attack probes across 11 backends — Lakera, NeMo, Presidio, Azure Content Safety, Bedrock Guardrails, LLM Guard, and five more — and outputs signed PDF and JSON comparison reports.

clauth

Streamlined AWS Bedrock setup for Claude Code - automated SSO, model discovery, and environment configuration

guardrailmesh

One enforcement layer for all your LLM guardrails. Drop in NeMo, Presidio, Lakera, OpenAI Moderation, Azure Content Safety, AWS Bedrock, LlamaFirewall, or LLM Guard — swap backends without touching your app code. Async-native. Covers OWASP LLM Top 10 attack categories.

mcp-server-bedrock-image

MCP server for AI image generation and manipulation using Stability AI models on AWS Bedrock. 10 tools: generate, edit, upscale, brand.

kubrick-cli

Agentic coding CLI for local models (Ollama, vLLM, llama.cpp) and Anthropic, OpenAI, and Amazon Bedrock.

github-kb

Ask questions about any GitHub repository with a repository-aware AI agent built with Python, Strands Agents, and AWS Bedrock.