Labs · open source
Built in the open.
Open source tools built for our own work, published under the MIT license. Each tool addresses part of the context problem, including internal system awareness, external intelligence feeds, and verified execution records.
github.com/adjective-rob01Internal context
Internal context
What an agent knows about the environment it works in.
TypeScript · MIT
Prelude
Machine-readable context for codebases. Prelude writes a project’s stack, architecture, decisions and module map into a .context/ folder and serves it to agents over MCP. Every session starts already knowing the code.
adjective-rob/prelude
(opens GitHub in a new tab)npm i -g prelude-contextRust · JavaScript · Python · MIT
Snap
Visual feedback for coding agents. Press a hotkey, circle the problem, type a label. The annotated screenshot and its structured metadata land in an inbox your agent reads over MCP.
adjective-rob/snap
(opens GitHub in a new tab)
02External context
External context
What an agent knows about the world outside it.
Python · MIT
Sonde
A registry for collection intent. Declare topics, queries, sources and scoring rules for GitHub, arXiv, Hugging Face, RSS and web monitors in versioned files. Simulate before you collect, and trace every artifact back to the topic version that produced it.
adjective-rob/sonde
(opens GitHub in a new tab)TypeScript · MIT
USASpending MCP
Federal contract data for AI assistants. 18 tools over USASpending.gov for searching awards, profiling agencies and contractors, and running business development workflows. Public data, no API key.
adjective-rob/usaspending-mcp
(opens GitHub in a new tab)npx -y federal-spending-mcp
03Governed execution
Governed execution
How an agent’s own actions are carried out and recorded.
From parts to a system