Unblocked Context Engine Workshop

Document Query Engine is an open-source workshop project from Unblocked that turns natural-language questions about GitHub pull requests and issues into validated MongoDB aggregation pipelines. It provides structured access where semantic retrieval cannot reason about time, relationships, or precise filters, using a six-step pipeline covering schema discovery, identity resolution, query synthesis, validation, error-feedback retries, and full-text search. The project includes a web query playground and chat agent, with Bun and TypeScript, MongoDB, GitHub data ingestion, and an LLM SDK for Anthropic or OpenAI. The repository starts with the query engine stubbed and guides users through implementing it.

Unblocked is a context engine for agentic software development. It gives coding agents permissions-aware context from source code, pull requests, conversations, documentation, issues, and production or incident history, helping them use the reasons behind code changes rather than code search alone. Its open-source document query engine uses automatic schema discovery, identity resolution across systems, plain-language-to-database query generation, validation that blocks dangerous operators, error-fed retries, and full-text search. The project also includes a context-engine simulator for testing whether pre-gathered context improves agent tasks. In the demonstrations, attaching Unblocked context to Claude sessions reduced token cost by about half and helped trace a regression to a model switch before creating a fix pull request.

Agent Context Workshop is a hands-on workshop resource for building and evaluating context layers for coding agents. It uses selected crates from the Qdrant Rust codebase to extract syntax with tree-sitter, resolve symbols and relationships with rustdoc JSON, store the resulting code knowledge graph in Neo4j, and expose graph tools such as search, blast-radius analysis, and implementor lookup to an agent. The workshop compares graph-based agents with grep-style agents using gold-verified questions, deterministic scoring, cached evaluation results, tool-adoption measurements, and trace inspection. Additional notebooks cover static Python resolution with Griffe and an optional Fenic-and-LLM semantic layer. The GitHub repository maintains the workshop through ordered Jupyter notebooks, typed extraction and graph code, evaluation harnesses, tests, committed Qdrant seed data, and a committed evaluation cache; it is licensed under Apache-2.0.

Context Engine Simulator is an open-source tool for creating context bundles locally and A/B testing agent tasks with and without pre-gathered context. It is presented as a way to test whether additional context from sources such as pull requests, Slack threads, and incident history improves coding-agent tasks and reduces token use.

Context Ontology Accelerator is an open-source semantic context layer for AWS and AI agents. It combines knowledge graphs, formal ontologies, rule-based systems, and modern AI in a Scan → Model → Serve workflow: it connects data sources, discovers schemas, enriches metadata, and ingests documents; induces and manages ontologies, defines metrics, and builds a unified semantic graph; then serves context through SPARQL federation using a Virtual Knowledge Graph, knowledge-graph traversal, queries, and MCP tools. The repository includes source-ingestion services for databases and documents, ontology induction and reasoning with HermiT and ELK, an Ontop-based Virtual Knowledge Graph, a context manager for query orchestration, and a React frontend. Access is controlled through namespace isolation and role-based authorization, with namespace-scoped roles and platform-level roles. The implementation uses Python and TypeScript, AWS CDK, Smithy-generated API contracts, and an Nx-managed monorepo; the project is licensed under Apache License 2.0.