Open Source Projects

A reusable system of expert collectives ('trusts') that turns AI assistants into a room with friction: real named figures in plausible settings, a moderator who refuses to skip steps, and a synthesis that names what was traded away. Ships as Cursor and Claude Code plugins, per skill zips, and a published MCP server (@bahulneel/brain-trust-mcp).

• Composable Agent Skills following the agentskills.io specification: expert opinion, draft experts, and ten bt-* workshops and editorials (software systems, codebase tactics, prompt engineering, design patterns, product strategy, organisation design, frontend UX, visual communication, technical writing, science explanation)
• Bounded guest drafting via an MCP served persona taxonomy of ~80 named figures: closes off invented authority and lets one room draft a witness from another's domain
• Shared protocol fragments (readings, synthesis, persona fidelity) reused across rooms; a new room is one YAML stanza and a paragraph of framing
• Monorepo of brain-trust-core, brain-trust-db, brain-trust-mcp (published as @bahulneel/brain-trust-mcp on npm) and repo-tooling, with releases producing Cursor and Claude Code plugin zips and standalone RPL.md / LRPL.md prompt artifacts
• Spawned RPL (Relational Prompt Language) as a separate, reusable artifact; see the RPL project entry

A Markdown embedded reasoning framework with associated logic for structuring how an LLM reasons about a user's request. Instead of relying on highly tuned prose and guessing what the model inferred, RPL lets you declare explicit relations, goals, and constraints so reasoning state becomes inspectable, queryable, and continuable across context boundaries. Spawned out of Agent Brain Trust and published as a standalone artifact.

• Stratified relational reasoning: each conversation turn is a stratum, the trace is the continuity mechanism between strata and across sessions
• Grounded in Bloom and the CALM theorem (Hellerstein; Ameloot, Neven & Van den Bussche): the monotonic core needs no coordination, with non monotonic operations made explicit as agent judgment points
• Base RPL (eager) and LRPL (lazy extension with memos, satisfactory quiescence, and a small stdlib including $json, $write, $index)
• Prose first authoring: Markdown is materialised into relations on encounter; relation heads attach to headings only where prose drifts
• Distributed as published RPL.md / LRPL.md artifacts inside the Agent Brain Trust releases, with a normative base specification and tutorials

Universal type primitives and axiomatic systems for TypeScript. Implements lazy typing: write type safe code against semantic axioms while deferring shape specific canon implementations to runtime registration. Published and usable; still evolving as the RelationalFabric ecosystem matures.

• Axioms, Canons, and Universal APIs: semantic concepts decoupled from data shape
• Published on npm (@relational-fabric/canon) with CLI scaffold and bundled toolchain
• Transparent ADRs and a public technology radar

A logical primitive for truly relational data systems: composable propositions backed by deterministic predicates, in the spirit of the Curry–Howard correspondence. Early library; depends on patterns still landing in Canon and Suss, as set out in the writing on claims and validation.

• Value semantics and verifiable equality for arbitrary data
• Claims backed by pure, deterministic predicates
• Compositional propositions mirroring domain relationships

Reference TypeScript implementation of RaCSTS (Relational and Causal State Transition System): serialisable propagator networks as first class values. Early reference code alongside the published specification.

• Bidirectional constraints with automatic reconciliation
• Leader free consensus via Sync; causal ordering via a Hybrid Epoch Clock
• Full pack/unpack of networks as values for portability and replay

Planned platform surface for truly relational, data driven systems: construction primitives where relationships carry semantic meaning. The ecosystem is taking shape first through Canon, Howard, and Suss; the meta repository and named platform libraries (Filament, Weft, Warp, Shuttle) follow once those foundations stabilise and selected patterns from a confidential client engagement can be ported.

• Active development lives in Canon, Howard, and Suss rather than this umbrella repo
• DCSGS whitepaper published; implementation detail remains under NDA pending extraction
• Filament, Weft, Warp, and Shuttle name the intended platform surface, not shipped libraries yet

Vue and Nuxt framework for Relativistic UI: frames, fields, intent queries, and variant assembly without prop drilling semantic context. Paused until RelationalFabric reaches a stable base and a retrospective pass on the confidential client front end (under NDA) is complete.

• Substantial codebase; patterns published separately (Relativistic UI, Set High Act Low)
• Mouldable components and planning based interaction chains
• Resumes against a stable RelationalFabric foundation