About Doug Fir Labs
Setting the foundational layers in neuro-symbolic AI architecture — where machines learn to reason, not just predict.
We're developing high-performance reasoning systems for verifiable, structured intelligence.
What we build
The AI stack has mature layers for prompts, tool calls, retrieval, orchestration, and logging. It has no layer for reasoning itself. Doug Fir Labs builds that layer: neuro-symbolic architecture that lets models reason over explicit structure, and reasoning protocols that carry that structure through a real system without losing accountability.
- Scholialang, a protocol layer for AI reasoning: typed claims, evidence, assumptions, decisions, contradictions and closure as content-addressed atoms that survive handoff between models, tools and reviewers. scholialang.org · reference implementation · specification · MCP server and plugins
- Traceblox, reasoning traces for agent sessions, shipping as a free local connector and a hosted service. In development. traceblox.com
- mcp-heartbeat, vendor-neutral heartbeat and liveness semantics for MCP participants. MIT. github.com/dougfirlabs/mcp-heartbeat
Contact
- General
- info@dougfirlabs.com
- Investors
- founders@dougfirlabs.com
- Source
- github.com/dougfirlabs
- Social
- x.com/dougfirlabs
- Office
- Seattle, WA, USA
- For agents
- /llms.txt