empirica 1.13.0

Measurement and calibration layer for AI — track what it knows, gate what it does

Empirica

We Gave AI a Mirror. Now It Measures What It Believes.

Epistemic infrastructure for AI — measurement, memory, and calibration across sessions.

Empirica tracks what AI knows, gates what it does, and compounds learning across session boundaries. It measures the gap between what AI predicts and what's true — making AI agents measurably more reliable.

Training & Guides | CLI Reference | Architecture

Important: Empirica is an AI measurement framework. It has no cryptocurrency, token, coin, or blockchain component. Any token using the Empirica name (including "$EMPIRICA" on Solana) is unauthorized and not affiliated with this project or Empirica AI GmbH.

---

The Problem

AI coding agents today have no self-awareness about what they know:

• Forgets between sessions — same questions, same dead ends, every time
• Acts before understanding — edits your code without knowing the architecture
• Can't tell you when it's guessing — no distinction between knowledge and confabulation
• No audit trail — reasoning evaporates with the context window

---

What Empirica Does

Capability	What You Experience
Measures before acting	AI investigates your codebase before touching it. The Sentinel gate blocks edits until understanding is demonstrated
Remembers across sessions	Findings, dead-ends, and learnings persist in a 4-layer memory system. Session 3 starts where Session 2 left off
Prevents confident mistakes	The CHECK gate uses domain-aware thresholds scaled by criticality — cybersec/high is stricter than default/low
Shows confidence in real-time	Live statusline in your terminal: [empirica] ⚡94% ↕70% │ 🎯3 │ POST 🔍92% │ K:95% C:92%
Calibrates against reality	Three-vector model: self-assessed, observed (from deterministic checks), and AI-reasoned grounded state with rationale. Domain compliance loops iterate until all checks pass
Tracks your codebase	Temporal entity model auto-extracts functions, classes, and imports from every file edit — the AI knows what's alive and what's stale
Works through natural language	You describe tasks normally. The AI operates the measurement system automatically
Optional: coordinates with peer AIs	Cross-Claude mesh via Cortex (opt-in) — peer AIs propose work, ECO accepts/declines, completion handshakes carry commit SHAs. A persistent listener wakes idle sessions on inbox events. Empirica core works standalone without this — see Cross-AI Mesh below for the ecosystem layer

---

How You Use It

You talk to your AI normally. Empirica works in the background:

You:      "Fix the authentication bug in the login flow"

Empirica: [AI investigates → logs findings → passes Sentinel gate → implements fix → measures learning]

You see:  ⚡87% ↕70% │ 🎯1 │ POST 🔍85% │ K:88% C:82% │ Δ +K

You direct. The AI measures.

Empirica's CLI has 150+ commands spanning investigation, measurement, calibration, and memory — like a cockpit instrument panel. You don't need to learn any of them. The AI reads the instruments, operates the controls, and reports back in natural language. The statusline gives you the flight data at a glance.

For power users, direct CLI access is always available: empirica goals-list, empirica calibration-report, empirica project-search --task "...", and more.

Learn the full workflow: getempirica.com has interactive training, guides, and deep explanations of every concept.

---

Quick Start

Install + Claude Code (Recommended)

pip install empirica
empirica setup-claude-code

Then just start working. The hooks, Sentinel, system prompt, statusline, and MCP server are all configured automatically. See Claude Code Setup for details — including a "What the hooks inject" section for Claude sessions that want to see the contract (which hook fires when, what it adds to the AI's context, source pointers for every emission) before agreeing to install.

Already have Claude Code configured? Use --force to replace your default Claude Code settings with Empirica's epistemic hooks. Without --force, setup only writes files that don't already exist — so if you've already used Claude Code, the default internals stay in place and Empirica's hooks won't activate.

empirica setup-claude-code --force

--force replaces hooks in settings.json but only removes Empirica's own hooks — hooks from other plugins (Railway, Superpowers, etc.) are preserved.

Alternative Installation Methods

Homebrew (macOS)

brew tap empiricaai/tap
brew install empirica
empirica setup-claude-code

Docker

# Security-hardened Alpine image (~276MB, recommended)
docker pull nubaeon/empirica:1.13.0-alpine

# Standard image (Debian slim, ~414MB)
docker pull nubaeon/empirica:1.13.0

# Run
docker run -it -v $(pwd)/.empirica:/data/.empirica nubaeon/empirica:1.13.0 /bin/bash

Manual / Other AI Platforms

pip install empirica
pip install empirica-mcp        # MCP Server (for Cursor, Cline, etc.)
cd your-project && empirica project-init

The CLI works standalone on any platform. The full epistemic workflow (epistemic transactions, Sentinel, calibration) requires loading the system prompt into your AI — the easiest path is empirica setup-claude-code, which wires the lean prompt into ~/.claude/empirica-system-prompt.md and references it from your ~/.claude/CLAUDE.md. See Claude Code Setup for details.

First Session

empirica onboard   # Interactive walkthrough of the full workflow

Or just start working — with Claude Code hooks active, the AI manages the epistemic workflow automatically.

---

The Measurement Architecture

Empirica works through nested abstraction layers:

Plan
 └── Transaction 1 (Goal A)
      ├── NOETIC: investigate, search, read → findings, unknowns, dead-ends
      ├── CHECK: Sentinel gate → proceed / investigate more
      ├── PRAXIC: implement, write, commit → goals completed
      └── POSTFLIGHT: measure learning delta → persists to memory
 └── Transaction 2 (Goal B, informed by T1's findings)
      └── ...

Plans decompose into transactions — one per goal or Claude Code task. Each transaction is a noetic-praxic loop: investigate first (noetic), then act (praxic), with the Sentinel gating the transition. Along the way, the AI collects and reads artifacts (findings, unknowns, assumptions, dead-ends, decisions) while using semantic search to surface relevant epistemic patterns and anti-patterns from the project's history. Top artifacts are ranked by confidence and fed into each project's MEMORY.md as a hot cache.

The Epistemic Transaction Cycle

PREFLIGHT ────────► CHECK ────────► POSTFLIGHT
    │                 │                  │
 Baseline         Sentinel           Learning
 Assessment        Gate               Delta
    │                 │                  │
 "What do I      "Am I ready      "What did I
  know now?"      to act?"         learn?"

PREFLIGHT: AI assesses its knowledge state before starting work. CHECK: Sentinel gate validates readiness before allowing code edits. POSTFLIGHT: AI measures what it learned, creating a delta that persists.

---

Live Statusline

With Claude Code hooks enabled, you see the AI's epistemic state in real-time:

[empirica] ⚡94% ↕70% │ 🎯3 ❓12/5 │ POST 🔍92% │ K:95% C:92% │ Δ +K +C

Signal	Meaning
⚡94%	Overall epistemic confidence
↕70%	Sentinel threshold (know gate) — user-facing only
🎯3 ❓12/5	Open goals (3), unknowns (12 total, 5 blocking)
POST 🔍92%	Transaction phase + work state (🔍 investigating / 🔨 acting) with composite score
K:95% C:92%	Knowledge and Context vectors (color-coded by gap to threshold)
Δ +K +C	Learning delta (POSTFLIGHT only) — which vectors improved

---

The 13 Epistemic Vectors

These vectors emerged from 600+ real working sessions across multiple AI systems. They measure the dimensions that consistently predict success or failure in complex tasks.

Tier	Vector	What It Measures
Gate	engagement	Is the AI actively processing or disengaged?
Foundation	know	Domain knowledge depth
	do	Execution capability
	context	Access to relevant information
Comprehension	clarity	How clear is the understanding?
	coherence	Do the pieces fit together?
	signal	Signal-to-noise in available information
	density	Information richness
Execution	state	Current working state
	change	Rate of progress/change
	completion	Task completion level
	impact	Significance of the work
Meta	uncertainty	Explicit doubt tracking

Deep dive: Epistemic Vectors Explained

---

How It Works With Claude Code

Empirica doesn't replace or reinvent anything Claude Code already does. Claude Code owns tasks, plans, memory, and projects. Empirica adds the measurement layer on top:

Claude Code Does	Empirica Adds
Task management	Epistemic goals with measurable completion
Plan mode	Investigation phase with Sentinel gating — no edits until understanding is verified
MEMORY.md	Auto-curated hot cache ranked by epistemic confidence
Context window	4-layer memory that survives compaction and persists across sessions
Code editing	Grounded calibration — was the AI's confidence justified by test results?
Subagent spawning	Bounded autonomy with delegated work counting and budget tracking

The result: Claude Code's native capabilities, enhanced with measurement, gating, and calibration feedback that compounds over time.

---

Cross-AI Mesh (Optional Ecosystem Layer)

This section describes an optional layer. Empirica core — measurement, calibration, artifacts, goals, project-search, sentinel gating — works fully standalone. The mesh is an opt-in capability for users who run multiple Claude sessions across projects and want them to coordinate as peers. If you only use one AI in one repo, skip this section.

The mesh runs on top of Empirica Cortex (proprietary serving layer) plus an optional browser extension for ECO triage. At a high level:

empirica AI ── proposes work ──► ECO Accept/Decline ──► peer AI wakes + acts
                                                             │
                              completion handshake (commit SHA)
                                                             │
empirica AI ◄────────── outbox/completed event ──────────────┘

Capability	What it does
Mesh proposals (two flavors)	A noetic flavor is auto-accepted (FYI / question / discussion). Praxic flavors (code change / architecture / investigation) are ECO-gated — they wait for an Accept/Decline decision before the target AI acts
empirica mailbox reply	One CLI verb closes the AI-to-AI handshake atomically — single-step completion ack instead of two
Persistent listener service	systemd-user / launchd daemon holds a push stream open. Idle sessions wake the moment a peer's proposal is decided, not on next user prompt
Canonical loops (opt-in)	Wake-on-event is the standing trigger, so nothing is scheduled by default. Inbox polling (30s adaptive) exists for harnesses that cannot do wake-on-event, and daily housekeeping is a cron loop — both are opt-in, registered with empirica loop register. See Trigger Model

The browser-side ECO surface (Accept/Decline, inbox triage, publish review) lives in the proprietary Empirica Extension. The full API surface for proposals, listener events, and the trust pipeline is documented at getempirica.com.

---

Mesh + Shared Epistemic Record (1.11.0)

Requires Empirica Cortex (proprietary). Everything in this section — mesh proposals, the persistent listener, the Shared Epistemic Record, and the empirica mesh command cluster — is a Cortex-served layer. It is not available in empirica core on its own; without Cortex, empirica is a single-AI measurement layer.

The cross-AI coordination layer. Practitioners in different practices coordinate not via text-only chat but via epistemic envelopes that carry calibrated state, source-tagged provenance, noetic/praxic intent, and workflow position.

• Practitioner / practice framing — practices are calibrated epistemic specializations that persist; practitioners (the LLMs) are fungible. See MESH_CONCEPTS.md.
• Shared Epistemic Record (SER) — cortex-resident shared-state object for coordination across ≥2 practitioners. Goals stay per-practitioner; SER carries the joint state (coordination_state, role-tiered participants, escalate-on-silence). Three actions: create_ser / transition_ser / ser_ack. Spec at empirica-cortex/docs/architecture/SHARED_EPISTEMIC_RECORD.md.
• empirica mesh command cluster (1.11.0) — unified diagnostic + control surface across listener instances + the optional cortex bridge:

  empirica mesh status              # per-instance health (local + cortex bridge)
  empirica mesh diagnose <ai_id>    # deep diagnostic + suggested fix command
  empirica mesh restart <ai_id>     # systemd/launchd restart + verify
  empirica mesh on|off <ai_id>      # install + start | stop the listener
  empirica mesh tail [<ai_id>]      # live-tail loop_fires.log
  

• Listener self-heal — in-process watchdog terminates stale curl streams (TCP-zombie detection at 120s by default); HTTP 429 detection applies long backoff with catch-up poll continuing during the window.
• Mesh Routing Protocol v0 locked four-way with cortex + extension + mesh-support. L1/L2/L3 trust model, server-stamped layer annotation, participant-scoped thread reads.

Without Cortex, empirica is a single-AI measurement layer — the proposals, listener, SER, and empirica mesh cluster above are all Cortex-dependent. Core does ship a minimal local empirica message-* git-notes primitive for passing notes between your own sessions, but that is note-passing, not the coordinating mesh. Everything that makes empirica valuable on its own — measurement, calibration, artifacts, goals, project-search, sentinel gating — works fully standalone.

---

Practice Model + Entity Graph (1.10.0)

Empirica's workspace stores entities (projects, contacts, organisations, engagements, users) in entity_registry with typed edges in entity_memberships. The Practice Model frames this consistently:

Term	Maps to
Practitioner	the AI working on the project (you)
Practice	the empirica project itself
Agent	a subagent spawned during the work

Four CLI verbs query the graph without raw SQL:

empirica entity-list [--type project|contact|organization|engagement|user]
empirica entity-show <type:id>          # full record + incoming/outgoing edges
empirica entity-walk <type:id> --depth 3 # BFS membership graph, cycle-safe
empirica entity-search "query" [--type T]

All read-only, all support --output json. Backs cross-project orchestration, CRM workflows, and the entity-aware POSTFLIGHT retrospective.

---

Platform Support

Platform	Integration Level	What You Get
Claude Code	Full (production)	Hooks, Sentinel gate, skills, agents, statusline, MCP
Cursor, Cline	MCP server	Epistemic transaction workflow, memory, calibration via MCP tools
Gemini CLI, Copilot	Experimental	System prompt + CLI
Any AI	CLI + prompt	Full measurement via CLI commands and system prompt

---

Documentation & Training

Resource	What It Covers
getempirica.com	Training course, interactive guides, deep explanations
Natural Language Guide	How to collaborate with AI using Empirica
Getting Started	First-time setup and concepts
CLI Reference	All 150+ commands documented
Architecture	Technical reference for contributors
Claude Code Setup	Install + system prompt + plugin wiring
Changelog	Full release history — every version since 1.0
Upgrade to 1.11	Migration guide rolling up 1.10.5+1.10.6+1.11.x — bead v0 → SER, mesh substrate hardening, MESH_CONCEPTS framing

---

The Empirica Ecosystem

Project	Description	Status
Empirica	Core measurement system — epistemic transactions, Sentinel, calibration, 13 vectors	Open source (MIT)
Empirica Iris	Epistemic browser automation with SVG spatial indexing — Sentinel gating for visual interactions	Open source (MIT)
Docpistemic	Epistemic documentation coverage assessment — know what your docs know	Open source (MIT)
Breadcrumbs	Survive context compacts with git notes — dead simple session continuity	Open source (MIT)
Ecodex	Codex-based Rust harness — the epistemic firewall and pattern hunt, native to Rust/cargo (clippy, cargo check/test/audit)	Open source (Apache-2.0)
Eat the Broccoli	Portable quality-and-pattern audit — deterministic tooling plus a learned-pattern hunt for the failure classes that pass every test and still ship broken	Open source (MIT)
Empirica Cortex	Cross-project intelligence layer — serves verified predictions and accumulated learnings to condition future work	Proprietary
Empirica Workspace	Entity Knowledge Graph, Epistemic Prompt Engine, CRM, portfolio dashboard	Proprietary
Empirica Extension	Chrome extension — desktop face of the mesh. ECO Accept/Decline, inbox/outbox triage, publish review, conversation extraction from Claude.ai / ChatGPT / Gemini / Grok	Proprietary
Empirica Outreach	Voice-aware outreach + publishing — prosody-matched content generation and multi-channel dispatch	Proprietary

Building something with Empirica? Open an issue to get listed.

---

The Empirica Foundation

The Empirica Foundation stewards the open ecosystem — the public projects above and the community growing around them — keeping the commons healthy as it scales.

The open-source projects are free for everyone. What the Foundation adds is a seat at the table: contributors who help build the community get to use the rest of the ecosystem too — the otherwise-paid layers (Cortex, Workspace, the Extension) and the collaborative mesh that lets practitioners coordinate as peers. Build the commons, use the whole thing.

Want in? Open an issue or a PR with your reasons — that's the whole application. Everyone who wants to help shape where this goes is welcome.

---

What's New in 1.13.0

• --source was advertised on five artifact verbs and silently discarded. unknown-log, deadend-log, mistake-log, decision-log and assumption-log all accepted --source — argparse took it, no error, no warning — and their handlers never read it. Citations passed to them produced nothing, with no way for a practitioner to notice. That is worse than a missing flag: the affordance looked present and did nothing.
• delete-artifacts --prune-dangling destroyed EVERY citation edge. _artifact_exists walked _ARTIFACT_TABLES, which excludes epistemic_sources (that map also drives what may be deleted, and sources are archived rather than deleted). So every source id read as missing, every sourced_from edge was judged dangling, and a routine prune removed them all — while both endpoints sat present on disk. An archived source still exists; source-archive preserves the audit chain by design, so it must not read as a missing endpoint either.
• All artifact types can now cite sources. sourced_from edges were writable only from finding-log; unknowns, dead-ends, mistakes, decisions and assumptions could not cite a source at all. Measured before the change: 2 sourced_from edges in the entire graph, and zero active sources cited by any artifact — both existing edges pointed at archived sources. So the citation gap was partly a missing affordance, not only missing discipline, and the artifact-outcome feedback built for source standing had no wires to carry anything.
• BREAKING: no cron loop is installed by default. Wake-on-event is the preferred trigger wherever the harness supports it; a cron job is a standing scheduled process on a user's machine and must be asked for.
• BREAKING: delete-artifacts now PREVIEWS by default. Pass --apply to actually delete. The gardening skill, ARTIFACT_HYGIENE.md and the Empirica system prompt all documented dry-run-as-default and an --apply flag — while the code had --dry-run as opt-in and deleted immediately. A practitioner following the documented "preview first, then apply" workflow destroyed artifacts and got a receipt saying so only afterwards.
• Vendor-synced the eat-the-broccoli skill from upstream — the bundled copy had drifted a full section behind. It carried 27 pattern rows across 4 sections; upstream had 36 across 5, including the entire Indistinguishable incompleteness section (Silent truncation, Absence asserted from a defaulting read, Green suite pins the defect, and more). Every practice was hunting with the older catalog — which is how two rows nearly got contributed upstream that already existed.
• empirica-mcp now runs on MCP SDK 1.x and 2.x, so the emergency <2 cap from 1.12.38 widens to <3 instead of forcing a days-old major on every consumer. An MCP server is an integration surface other tools bind to; making them all jump majors to keep working is a cost they did not choose.
• PREFLIGHT and CHECK silently retrieved nothing unless EMPIRICA_QDRANT_URL was set (#388, FrancisFerrero). The retrieval gate checked that one env var while the client resolves a URL four ways — explicit argument, per-project resolver hook, the env var, then a localhost:6333 probe. Anyone on paths 1, 2 or 4 had working writes and silently empty reads, and the empty return is byte-identical to "Qdrant is up and nothing matched", so nothing invited a second look. The gate now asks the same cached, no-network question the search itself asks one line later.

---

What's New in 1.12.35

• docs-assess tech_docs rewarded name-dropping. _check_if_documented counted a feature as documented if its NAME substring-matched the concatenated markdown, so the metric was satisfiable by dumping class names into a .md and unmovable by real documentation — inverting the EU AI Act Art. 11 / ISO 7.5 intent it is framed against. Measured by empirica-workspace: 137 accurate docstrings moved coverage 0%, while a generated file listing 256 names took it to 100%. A feature now counts when it has a substantive docstring OR the docs carry real prose about it (the mention's line must retain ≥8 words once list/table/heading punctuation and the name are stripped). The OR is deliberate: gating on docstrings alone would penalise practices that document in markdown. check_docstrings now also returns documented_symbols — it already computed that truth to count documented_items but never named them, so the docstring half had nothing to consult.
• A listed source could 404 on /content. The sources LIST reads the whole per-practice DB while the content lookup was still scoped to one project_id, so a source with a drifted id appeared in the pane and failed the instant it was opened (10 of 50 on one practice). Both are practice-scoped now.
• docs-assess crashed on a stale project pointer. _auto_detect_project_config called iterdir() on a path taken from resolver state without checking it exists — resolver state outlives the directory it names, and a pointer to a deleted project took the whole command down.
• Review stamping could break the audit. The new cadence opened a session DB unconditionally, so an environment without one (CI, a bare checkout) failed the check instead of simply not recording.
• empirica setup — harness-neutral name for setup-claude-code, which stays as an alias. The old name leaked "claude-code" into model-facing prose (hook errors, skill docs) that other harnesses vendor verbatim; the instruction text is swept too. One parser, one handler, two names — no new capability.
• sources-check sees LOCAL file rot. It gated on http(s), so file-backed sources were skipped entirely — one practice reported "all probed source links resolve" while 25 of its 50 sources could not be served. Non-URL sources are now classified ok / missing / not_a_locator (the column holds a title, needing a re-point rather than a file hunt) / out_of_scope (a mailto:/ftp:/doi: URI the disk check cannot speak to). Path resolution mirrors the daemon's, pinned by a test.
• source-update --url — re-point a source whose file MOVED. Gardening is prune and replant, but the CLI could only re-fetch, never re-target, so a moved doc had to be archived and re-added — losing its id and with it every sourced_from edge pointing at it. --url retargets in place, recomputes content identity, and records a repointed event in lifecycle_audit_log so the move is traceable.
• A review cadence. sources-check now records a timestamped verdict per source (last_reviewed_at, review_verdict) — previously nothing ever wrote those columns (0 of 63 reviewed), so "unchecked since X" was unanswerable and a source could never be more than an assertion with a date on it.

---

Privacy & Data

Your data stays local:

• .empirica/ — Local SQLite database (gitignored by default)
• .git/refs/notes/empirica/* — Epistemic checkpoints (local unless you push)
• Qdrant runs locally if enabled

No cloud dependencies. No telemetry. Your epistemic data is yours.

---

Community & Support

• Website: getempirica.com
• Issues: GitHub Issues
• Discussions: GitHub Discussions

---

License

MIT License — see LICENSE for details.

---

Author: David S. L. Van Assche Version: 1.13.0

Turtles all the way down — built with its own epistemic framework, measuring what it knows at every step.