AIWeave

TeamWeave is a config-driven multi-agent orchestration platform that runs on AWS and lets teams define AI pipelines entirely through JSON configuration without requiring code changes to add new workflows or teams. The platform ships with two production-ready patterns—a Visibility Team for content marketing workflows and an Improvement Team for personal learning systems—each orchestrating multiple AI agents through a control plane that manages async executions and an execution plane that handles RAG context retrieval, prompt building, and Bedrock Agent invocation.

TaskWeave is an API-first agent framework built on LangChain and LangGraph that dynamically constructs and executes multi-step workflows from JSON configurations. It supports both explicit task chaining through the `/invoke` endpoint and automatic configuration generation via `/invoke/auto`, where users provide only a question and the system intelligently selects tools from a modular schema registry. The framework excels at orchestrating diverse task types—including LLM prompts, API calls, and data analysis—while maintaining shared memory across tool outputs to enable seamless data flow between steps.

ContextWeave is an AWS-native platform that combines GraphRAG and cache-augmented generation to answer deep, evidence-backed questions about developer expertise by ingesting Git repositories, architecture documents, and resume content into a knowledge graph. The system features a semantic response cache that short-circuits the full RAG pipeline for repeated queries, and an adaptive routing layer that automatically classifies documents, recommends optimal chunking strategies, and selects the best retrieval method based on self-improving feedback from Memgraph.

ScreenWeave is an AWS-native platform that crawls websites using Playwright to capture every visual state and interactive transition, storing structured artifacts in S3 for comprehensive analysis. It exposes two independent interfaces—an MCP endpoint for triggering crawls and retrieving screenshots, and a REST endpoint that feeds captured visuals through Claude 3.5 Sonnet via Amazon Bedrock to detect visual anomalies, regressions, and cross-page inconsistencies. The platform supports regression detection across deployments by allowing new QA jobs to reference prior session context, enabling teams to track visual changes over time with AI-powered analysis.

DeployWeave is a modular MCP tool suite that streamlines AWS Bedrock deployments by automating model selection, agent provisioning, LoRA adapter management, and real-time token enforcement. The platform intelligently selects optimal Bedrock models based on latency and cost budgets, provisions up to five agents transactionally with automatic rollback on failure, and manages a dynamic LoRA adapter catalog for fine-tuned model optimization.

CipherWeave is an agentic cryptography intelligence layer that automatically determines the optimal encryption strategy for AI agents based on data classification, regulatory requirements, and risk assessment. The system intercepts key-derivation requests, analyzes endpoint risk through a Memgraph topology graph, and returns a fully justified cipher strategy via a single MCP tool call, with support for quantum-safe algorithms like ML-KEM-768 and automatic just-in-time registration of unknown endpoints using Bedrock-inferred policy.

MCP Observatory provides a two-phase execution framework for safely handling high-risk MCP tool calls by separating planning from execution through a propose-and-commit pattern. The system evaluates tool proposals for uncertainty and integrity risks without side effects, then only executes when a cryptographically signed commit token validates the original proposal, with built-in replay protection and comprehensive verification rules. It includes generic wrappers, HMAC-SHA256 token management, optional Postgres storage, and demo scenarios showing real-world MCP server integration with end-to-end security flows.

DataDictionary is an MCP server that manages API field definitions stored in DynamoDB with AI-powered draft generation via Amazon Bedrock. It provides a complete read-write workflow where new data elements are proposed through natural language prompts, verified by MCP Observatory safety gates, and then committed to persistent storage. The tool combines intelligent field generation, proposal verification, and direct query capabilities to streamline the creation and maintenance of standardized API documentation.

DeviceWeave is an AI-native execution layer that translates natural language commands into safe, real-time control of IoT devices and scenes by combining semantic understanding with deterministic policy enforcement. The system uses a multi-tier resolution pipeline—starting with fast cosine similarity matching and escalating to Claude Haiku only when confidence falls below threshold—before any device I/O is permitted, ensuring that a policy engine evaluates every action against authored rules stored in DynamoDB.

# IntentWeave IntentWeave is a framework for building intent-driven applications that automatically route user requests to the most appropriate handlers based on semantic understanding. The system uses advanced natural language processing to parse user intent, extract relevant context, and intelligently dispatch tasks across distributed services without requiring explicit routing rules. Its distinctive strength lies in its ability to learn and adapt routing patterns over time while maintaining transparent, auditable decision-making for enterprise environments.

PromptWeave is a framework for composing and managing complex LLM prompts through a modular, template-based architecture. It enables developers to build reusable prompt components, chain them together with conditional logic, and maintain version control over prompt iterations. The tool stands out by providing a structured approach to prompt engineering that reduces duplication, improves consistency across applications, and makes it easier to test and optimize multi-step LLM workflows.

RoutineWeave is an AI-powered scheduled execution engine that automates routine tasks by running JSON-defined prompts on a cron schedule using Google Gemini. Users define tasks with prompts, cron schedules, and optional variables, upload them to S3, and the system automatically provisions EventBridge rules to execute them at the specified times. Results are delivered via AWS SNS to email, Slack, or webhooks, with built-in support for dynamic variables, retry logic, and Google Search grounding for real-time data integration.