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 240+ 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
Then just start working. The hooks, Sentinel, system prompt, statusline, and MCP server are all configured automatically.
empirica setup --harnesspicks the harness. It resolves from--harness, else$EMPIRICA_HARNESS, elseclaude-code. An unsupported harness is refused by name and nothing is written — previously it wrote~/.claude/regardless and reported success, which on any other harness configured a path that harness never reads.Codex is refused deliberately: ecodex is self-provisioning (it vendors the plugin into its own binary), so there is nothing here to write, and the refusal points you at that pipeline.
setup-claude-coderemains as an alias and pinsclaude-coderegardless of environment.
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 --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
Docker
# Security-hardened Alpine image (~276MB, recommended)
docker pull nubaeon/empirica:1.13.43-alpine
# Standard image (Debian slim, ~414MB)
docker pull nubaeon/empirica:1.13.43
# Run
docker run -it -v $(pwd)/.empirica:/data/.empirica nubaeon/empirica:1.13.43 /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, 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.
Removing it
empirica setup writes to eleven locations, and six of them are files Claude Code
owns and writes continuously. So uninstall shows you the plan first and only
removes what is actually ours:
empirica setup --uninstall # the plan — names every location, changes nothing
empirica setup --uninstall --apply # remove, reporting anything it refused
| Removed | the plugin directory, our system-prompt file, active_work.json, the listener service |
| Edited | settings.json, ~/.claude.json, the plugin registries — our keys only, yours untouched |
| Reported, never touched | the @include line in your own ~/.claude/CLAUDE.md |
That last row is deliberate. Setup appended one line to a file you author. If you have reorganised around it, we cannot tell which edit is safe — so uninstall tells you the line number and leaves the decision to you.
Two more things it will not do: it refuses rather than writing a shared config it
could not parse, and it refuses if Claude Code modified the file while uninstall
was preparing its write. In both cases nothing is removed and it says why. Your
.empirica/ project data — findings, goals, git notes — is never touched; this
removes the integration, not your epistemic record.
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.
16 skills ship with the plugin — the transaction discipline, graph gardening, the quality sweep, mesh messaging, and more. They are lazy: a skill does nothing until it loads, so knowing when each fires matters more than knowing what it holds. → Skills reference
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
Requires Empirica Cortex (proprietary). Everything in this section — mesh proposals, the persistent listener, the Shared Epistemic Record, and the
empirica meshcommand 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 atempirica-cortex/docs/architecture/SHARED_EPISTEMIC_RECORD.md. empirica meshcommand cluster — 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
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
Two harnesses are supported. Everything else is untested — prompt and rules files may exist for other tools, but their presence is not support, and we would rather say so than let you find out mid-project.
| Harness | Status | What you get |
|---|---|---|
| Claude Code | Supported | Full integration — plugin, hooks, Sentinel gate, skills, agents, statusline, MCP |
| Codex (via ecodex) | Supported | Self-provisioning: ecodex vendors the plugin into its own binary and loads hooks natively. empirica setup refuses codex by name and points you at ecodex's pipeline — that refusal is correct, not a gap |
| Antigravity (Google), Vibe (Mistral AI) | Not yet | Possible future support. Not now |
| Everything else | Untested | The CLI works anywhere Python does, but no harness integration is verified |
MCP is a fallback, not a second path
empirica-mcp exists for harnesses that cannot run the CLI integration —
Claude Desktop, Gipitee-style clients. Use it when you have no alternative.
The reason matters: an MCP surface cannot enforce the Sentinel gate the way a blocking pre-tool hook does. So an MCP-only deployment gives you the measurement layer with a weaker guarantee — the noetic/praxic firewall becomes advisory. That is a real difference in what the system promises, and it should be a deliberate choice rather than something you infer from a feature table.
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 240+ 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 1.13 | Migration guide for the 1.12.x → 1.13 jump — two deliberate breaking changes, both fail-safe. Older guides (1.9–1.11) live in docs/guides/ |
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 1.13.43
doctor --deploy-gaps— one readable answer to "what is committed but not live on this box", four lanes: unreleased commits (NEW check — count + headline subjects since the last tag; PASS with data, never WARN, because a non-zero queue is the normal state of a working repo), CLI-vs-checkout, deployed-plugin freshness, and core/MCP version match. A filter over the same checks doctor always runs, so the focused view cannot drift from the full one. Its first live run surfaced a real three-environment version skew on the development box itself.EMPIRICA_RETRIEVAL_BUDGET_S(default 30s) — a wall-clock budget over PREFLIGHT pattern retrieval, checked between phases. The retrieval chain runs a dozen sequential network calls after the transaction row commits, so a degraded backend never failed preflight — it made preflight lie to whoever wrapped it in a timeout (measured: MCP reporting failure on an open transaction at 128s; a 120s+ stall reproduced twice locally, every component fast when probed alone). Past the deadline, remaining phases are skipped and named in_retrieval_budget— a partial injection that says it is partial.preflight-submitreports atimingsblock when pattern retrieval takes ≥5s, so a stalled box names where the time went instead of needing a bisect.unknown-resolveaccepts--resolutionas an alias for--resolved-by— every sibling verb calls the field "resolution", so guessing it was the natural first attempt, and the friction at the right spelling is what pushed a reporter into fragile hand-quoting that corrupted an artifact.- win32: the CLI now works without any environment variables. UTF-8 is forced on stdout/stderr at the entry point (cp1252 killed the human renderer after the DB write committed, so successful operations looked failed); instance resolution falls back to the Windows Terminal session GUID and then a stable constant instead of
None(which left PREFLIGHT unable to resolve the project and the Sentinel silently blind); and the default Ollama embedding tag is the explicitqwen3-embedding:0.6b(the registry resolves the bare name to the 4096-dim build against our 1024-dim collections). - Sentinel: the loop-closed handler refused the file-argument preflight form its own error hint recommends — a second implementation of one policy that drifted. Fixing it exposed a third chain-blind site: transition matching accepted ANY segment of a chained command, so
cd /tmp && rm -rf /xrode through after POSTFLIGHT. Transition commands now require EVERY segment to be a transition or benign producer. empiricaCLI import-divergence warning is cwd-honest: it probes from a neutral directory AND the current one, distinguishing cwd-dependent resolution (a checkout shadowing site-packages), importable-only-here, and true install divergence — the old single probe reported agreement from exactly the directory where it was wrong.- MCP timeouts on transaction verbs carry the recovery protocol: the row commits before the slow tail, so a timeout does not mean the submit failed — the error now says to check
empirica statusbefore resubmitting, because resubmitting double-opens.
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: 1.13.43
Turtles all the way down — built with its own epistemic framework, measuring what it knows at every step.
1 maintainer
Release files for empirica 1.13.43
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| empirica-1.13.43.tar.gz | 2.6 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| empirica-1.13.43-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 5.3 MB
Release files / empirica-1.13.43.tar.gz
| Download URL | empirica-1.13.43.tar.gz |
|---|---|
| Size | 2.6 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
88ee1a2b7c3d72499e28d6bb433cfda83d5b6d0d82ddc56b5100cc17f765f0b5
|
|
BLAKE2b-256 checksum How to use checksums |
cc2e85d9a928605059e755ae775d707eb477b5c5c18ff1b7bfb68743c91b04e5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 10, 2026.
Transparency logRelease files / empirica-1.13.43-py3-none-any.whl
| Download URL | empirica-1.13.43-py3-none-any.whl |
|---|---|
| Size | 2.7 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
cb2dd349d109bdf173b6764e2c4e02f6024b84afab2b2e6211bfdec2af533fac
|
|
BLAKE2b-256 checksum How to use checksums |
d23cf621455aadb448c70f179590bc52f859ef9a67dcf3a0578f3a0863ab956a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 10, 2026.
Transparency log
