wheeler 0.9.8

Reliable, trustworthy, trackable AI workflows for science. A Claude Code-native research assistant with a provenance-tracked knowledge graph.

WHEELER

Reliable, trustworthy, trackable AI workflows for science.

Wheeler is a thinking partner for scientists, built natively on Claude Code. It gives you slash commands for each stage of research: discuss the question, plan the investigation, execute analyses, write up results. Every action is wrapped in a knowledge graph that tracks how research artifacts (papers, code, data, findings, drafts) depend on each other, making every AI-produced result traceable back to the exact script, data, and parameters that produced it.

Runs 100% locally. No API keys, no cloud services. Your data never leaves your machine.

Named after great physicist John Archibald Wheeler, Niels Bohr's longtime collaborator. Wheeler and Bohr worked by talking. Bohr would pace, thinking out loud. Wheeler would push back, sharpen the question, sketch the math. The best ideas emerged from the conversation, not from either person alone. That's the model here.

---

Quick Start

uvx wheeler init my-research-project
cd my-research-project && claude
/wh:start

That's it. The first command scaffolds the project (.plans/, .wheeler/, wheeler.yaml, .mcp.json) and installs slash commands and agents to ~/.claude/. The second drops you into Claude Code with Wheeler's MCP servers wired up. The third routes you to the right /wh:* command for what you want to do.

For long-lived use install Wheeler globally (faster startup, stable paths in .mcp.json):

uv tool install wheeler
wheeler init my-research-project

Run wheeler doctor any time to verify your setup (Python version, deps, Claude Code, Neo4j connectivity).

Prerequisites: Python 3.11+, uv, Claude Code (Max subscription), and Neo4j Desktop (free). New to all this? Walk through the Getting Started Guide.

From source

git clone https://github.com/maxwellsdm1867/wheeler.git
cd wheeler
uv sync --extra dev              # editable install + tests + ruff + mypy + build
uv run wheeler init ~/my-research-project

bin/setup.sh is still around for the full bootstrap (Neo4j in Docker, schema init, git hooks, zsh completions).

---

Why Wheeler

Science requires reproducibility. As AI gets embedded in research workflows, the gap between "AI helped me" and "here's the auditable chain of how this result was produced" becomes a credibility problem.

Wheeler is built on four pillars:

Traceable results. When Wheeler creates a finding, it automatically records what script ran, what data it consumed, what papers informed the approach, and when it happened. One tool call builds the full provenance chain. The agent focuses on science; infrastructure handles bookkeeping.

Change propagation. When a script changes or data is updated, Wheeler flags every downstream finding as stale and reduces its stability score. You always know what to trust and what needs re-verification.

Context management. All components read from and write to the same graph, so a finding from data analysis immediately informs subsequent literature searches, experimental design, and manuscript preparation. Information is progressively disclosed and retrieved only when relevant.

Executable research artifact. The knowledge graph moves beyond the static PDF. It is an executable map of discovery: any scientist can inherit the full experimental context of a project, explore how results connect, and build directly on top of prior work.

---

The Workflow

Wheeler gives you a fluid cycle, not a rigid pipeline. Enter at any point, skip stages, repeat them.

 TOGETHER         you + wheeler, thinking out loud
 discuss  plan  chat  pair  write  note  ask
                         |
                         v  remaining work is grinding
 HANDOFF          propose independent tasks
 handoff          you approve, modify, or keep talking
                         |
                         v
 INDEPENDENT      wheeler works alone
 wh queue "..."   logged, stops at decision points
                         |
                         v
 RECONVENE        results + flags + surprises
 reconvene        back to TOGETHER

Every plan and execution renders a self-contained visual brief: the question and sub-questions, figure mockups (pre-registered sketches) paired with the real result figures, a pipeline flow chart, and the data sources. /wh:discuss reads that brief to interpret the results with you like a colleague, referencing figures by number and running quick checks against the data to strengthen or disprove a point.

A typical session

The flow we design for, end to end:

1. /wh:discuss — talk through the question until it is sharp. Wheeler asks like a colleague, grounds the conversation in what the graph already knows, and locks the decisions.
2. /wh:plan — Wheeler structures the investigation into waves of tasks and, before any data is touched, pre-registers the figures: what each one plots and how competing hypotheses would look different in it. On approval it renders a visual brief (question, mockups, pipeline, data sources) so you react to a picture, not prose. Seeing the mockup often sends one more round of sharpening back into the plan.
3. /wh:execute — Wheeler runs the WHEELER-assigned tasks, logs findings with full provenance, then regenerates the brief as a report: each pre-registered mockup now sits beside its real result figure, success criteria are marked, and result tables tuck into dropdowns.
4. /wh:discuss (again, on the results) — hand Wheeler the brief and interpret together: what holds, what is fragile, what the next question is. Wheeler references figures by number, pulls related findings from the graph, and can run a quick check against the data to settle a contested point, registering whatever you endorse back into the graph.
5. /wh:write drafts from the endorsed findings with strict citations, or /wh:plan opens the follow-up investigation. /wh:close sweeps the session into a synthesis.

You can enter at any step, skip stages, or loop steps 2 to 4 as the work demands.

Commands

Command	What it does
/wh:start	Route to the right command (or type your task)
/wh:discuss	Think like a colleague: sharpen the question, or interpret a plan's results from its brief (runs checks against the data, cites figures by number)
/wh:plan	Structure tasks with waves, assignees, checkpoints; render a visual brief with figure mockups
/wh:execute	Run analyses, log findings with provenance; pair mockups with the real result figures in a report
/wh:write	Draft text with strict citation enforcement
/wh:ingest	Bootstrap graph from existing code, data, papers
/wh:add	General-purpose ingest: text, DOI, file, URL
/wh:note	Quick-capture an insight, observation, or idea
/wh:compile	Compile graph into synthesis documents with citations
/wh:dream	Consolidate: promote tiers, detect communities, link orphans
/wh:pair	Live co-work: scientist drives, Wheeler assists
/wh:ask	Query the graph, trace provenance chains
/wh:status	Show progress, suggest next action
/wh:handoff	Propose tasks for independent execution
/wh:reconvene	Review results from independent work

More commands

Command	What it does
/wh:chat	Quick discussion, no execution
/wh:triage	Triage GitHub issues against planned work
/wh:report	Generate work log from graph (time period)
/wh:close	End-of-session provenance sweep
/wh:pause / /wh:resume	Save and restore investigation state
/wh:update	Check for Wheeler updates
/wh:dev-feedback	File bugs from inside your session

Headless mode

Wheeler can run tasks without you present:

wh queue "search for papers on SRM models"   # sonnet, 10 turns, logged
wh quick "check graph status"                 # haiku, 3 turns, fast
wh dream                                      # graph consolidation

The wh launcher is a bash script in bin/wh that ships only with the source tree, not the PyPI wheel. To enable it after a uv tool install, clone the repo and symlink it: sudo ln -sf $PWD/bin/wh /usr/local/bin/wh. A native wheeler queue / quick / dream is on the roadmap.

Wheeler never does your thinking. Every task gets tagged: SCIENTIST (judgment calls), WHEELER (grinding), or PAIR (collaborative). Decision points are flagged as checkpoints, not guessed at.

---

How It Works

Provenance-completing tool calls

The core primitive: one tool call creates a finding AND its full W3C PROV-DM provenance chain. You never write this directly; slash commands handle it. But under the hood, this is what happens:

add_finding(
    description="Midget and parasol cells have similar clusters of fitted SRM parameters",
    confidence=0.85,
    execution_kind="script",                    # auto-creates Execution activity
    used_entities="D-abc123,S-def456",          # auto-links inputs
)

Wheeler internally creates the Finding, an Execution activity node, links inputs (Dataset, Script) via USED, links the output via WAS_GENERATED_BY, sets a stability score, and dual-writes to Neo4j and JSON. The provenance chain is always complete because the agent never had to remember to create it.

Stability and invalidation

Every entity carries a stability score (0.0-1.0) encoding epistemic trust: primary data = 1.0, published papers = 0.9, validated scripts = 0.7, LLM-generated findings = 0.3. When an upstream entity changes, stability decays downstream: new = source * (0.8 ^ hops). Changed scripts propagate stale flags through the entire dependency chain.

The knowledge graph

The graph is an index over files, not a document store. Each node stores an ID, type, tier, title, path, and timestamps. Full content lives in knowledge/{id}.json. Human-browsable rendering lives in synthesis/{id}.md (Obsidian-compatible with YAML frontmatter and [[backlinks]]). When you need connections, ask the graph. When you need content, read the file.

11 entity types: Finding, Hypothesis, OpenQuestion, Dataset, Paper, Script, Execution, Document, ResearchNote, Plan, Ledger.

14 relationship types: 6 W3C PROV standard (USED, WAS_GENERATED_BY, WAS_DERIVED_FROM, WAS_INFORMED_BY, WAS_ATTRIBUTED_TO, WAS_ASSOCIATED_WITH) + 8 Wheeler semantic (SUPPORTS, CONTRADICTS, CITES, APPEARS_IN, RELEVANT_TO, AROSE_FROM, DEPENDS_ON, CONTAINS).

50 MCP tools across 5 servers (mutations, queries, search, ops, legacy monolith).

See ARCHITECTURE.md for the complete technical spec: module dependency map, PROV schema, MCP tool listing, hardening patterns, design decisions.

---

What's New

v0.9.8 (2026-06-10): visual research briefs

• Visual research briefs: /wh:plan and /wh:execute now render a self-contained HTML brief (.plans/brief/<investigation>.html) that leads with the question and sub-questions, then figure mockups (inline SVG or synthetic-data PNG) paired with the real result figures at execute time, a pipeline flow chart, data sources linked into it, and collapsible data tables. Numbered sections and figures with legends so the brief is referenceable in discussion. Accessible by default: light/dark toggle, colorblind-safe status chips, WCAG-AA contrast.
• Figure intent is pre-registered: /wh:plan draws out what each figure will plot and how competing hypotheses would look different in it, then mocks it up so the scientist reacts before any data is touched.
• /wh:discuss is now a two-mode colleague: sharpen a question before planning, or interpret a plan's results from its brief or md file after it runs. Interpret mode references the report by figure and section number, pulls relevant graph context, runs scoped code to strengthen or disprove a point, and registers checks back into the graph with full provenance.
• Test suite at 1713 (was 1707 in v0.9.7).

v0.9.7 (2026-06-10): bug queue cleared

• Nine reported bugs fixed (#56 through #64): every open issue reproduced, fixed, and verified end-to-end against a live graph.
• show_node and graph_gaps hardened: show_node returns an actionable error instead of crashing when a packaged environment is missing wheeler.knowledge; graph_gaps gains limit/offset/summary parameters and per-bucket counts so its default response stays under the token cap on mature graphs.
• /wh:close made robust: close Executions always carry a non-empty started_at across all three triple-write layers, the session-boundary query ignores malformed timestamps and warns instead of silently falling back, and session-synthesis Documents validate via their close-Execution provenance.
• Mutation fixes: update_node field validation, figure titles, path dedup, and dataset type defaults (#57, #59, #61, #62); triple-write drift is now surfaced proactively in graph_health and the consistency summary (#60).
• DOI badge fixed: the citation badge is now served through shields.io so it renders reliably alongside the other badges.

v0.9.6 (2026-06-01) — Software citation

• Cite this repository: Added CITATION.cff so GitHub renders a one-click "Cite this repository" button (APA and BibTeX export), plus a Citation section in the README with a ready-to-paste BibTeX entry.
• Authorship recorded: Arthur Hong and Fred Rieke are now listed as authors and copyright holders across pyproject.toml, LICENSE, and the citation metadata.

---

Architecture

Claude Code (interactive)
    ├── /wh:* slash commands (.claude/commands/wh/*.md)
    │       ├── /wh:start: intent router (invokes other commands)
    │       ├── YAML frontmatter: tool restrictions per mode
    │       └── System prompt: workflow + provenance protocol
    │
    ├── MCP Servers (50 tools)
    │       ├── wheeler_core (12): health, status, context, search, cypher
    │       ├── wheeler_query (10): read-only query_* tools
    │       ├── wheeler_mutations (18): add_*, link, delete, update, merge
    │       ├── wheeler_ops (10): staleness, citations, consistency
    │       └── wheeler (legacy monolith): same 50 tools, one server
    │
bin/wh (headless)
    └── claude -p with structured logging → .logs/*.json

Code structure

wheeler/
├── models.py                # Pydantic v2: 11 node types, prefix mappings
├── config.py                # YAML loader, Pydantic config models
├── provenance.py            # Stability scoring, invalidation propagation
├── consistency.py           # Cross-layer drift detection and repair
├── mcp_server.py            # Legacy monolith: all 50 tools
├── mcp_core.py              # Split server: health, context, search (12)
├── mcp_query.py             # Split server: query_* read-only (10)
├── mcp_mutations.py         # Split server: add_*, link, delete, update (18)
├── mcp_ops.py               # Split server: staleness, citations (10)
├── mcp_shared.py            # Shared: trace IDs, decorators, config
├── knowledge/               # File I/O: read, write, list, render, migrate
├── graph/                   # Neo4j backend, circuit breaker, schema, context
├── search/                  # Embeddings, RRF fusion, graph-expanded search
├── validation/              # Citation validation, ledger quality metrics
├── tools/graph_tools/       # Provenance-completing mutations + queries
└── workspace.py             # Project file scanner

tests/                        # 1713 tests
docs/                         # Getting started, architecture, project spec

---

Contributing

Bug reports: Use /wh:dev-feedback from inside a session to file structured issues, or report at GitHub Issues.

Tests: python -m pytest tests/ -v (1713 tests). E2E tests require a running Neo4j: python -m pytest tests/e2e/ -v.

Architecture: See ARCHITECTURE.md for the full technical spec (module dependency map, PROV schema, MCP tool listing, hardening patterns).

Project docs:

• Mission — four pillars, target audience, design north star
• Tech stack — components, infrastructure patterns, current gaps
• Roadmap — shipped versions, v0.9.0 phases, v1.0 criteria
• Getting started — install walkthrough with Neo4j Desktop
• Project spec — original design specification

Citation

If you use Wheeler in your research, please cite it:

@software{hong_wheeler_2026,
  author    = {Hong, Arthur and Rieke, Fred},
  title     = {{Wheeler: Reliable, trustworthy, trackable AI workflows for science}},
  year      = {2026},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.20498885},
  url       = {https://doi.org/10.5281/zenodo.20498885}
}

License

MIT