Epoch README
The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Epoch listing page.
Epoch -- Time Estimation MCP Server
Epoch is a time estimation MCP server that helps engineering leads, agents, and planners who need calibrated duration estimates produce PERT/reference-class estimates and record actuals.
TL;DR: Epoch — time estimation MCP server. Best for engineering leads, agents, and planners who need calibrated duration estimates.
Epoch helps AI agents understand time.
AI can write code, analyze data, and build apps -- but it can't tell you how long something will take, what it'll cost, or whether a deadline is realistic. Epoch fixes that.
Show Me
Why Epoch?
Every AI agent hallucinates timelines. "This should take about 2 hours" becomes 2 days. Epoch gives AI grounded, data-driven estimates instead of guesses. It packages established estimation methods (PERT, COCOMO II, Monte Carlo, reference class forecasting) into 25 tools any AI can call -- so your assistant stops guessing and starts calculating.
Works out of the box. Epoch ships with a bundled reference database built from 117,791 real data points across task types, complexity levels, and estimation tools. You get accurate estimates from day one — no data collection or account setup required. If you choose to record your actuals, Epoch's self-improvement engine learns your patterns and gets even more precise over time.
What is MCP?
MCP (Model Context Protocol) is how AI assistants like Claude connect to external tools. Think of it like a plugin system -- you add Epoch with one command, and suddenly your AI assistant can estimate timelines, calculate business days, compare model costs, and predict whether your project will finish on time.
Quick Start
30-second setup -- works in Claude Code, Cursor, VS Code, and Windsurf:
That's it. Your AI assistant now has 25 time estimation tools.
Or add it to your project's .mcp.json:
Agent Skill
Epoch also ships a public agent skill at skills/epoch/SKILL.md. Use $epoch in compatible agent hosts when you want the agent to choose the right Epoch MCP or CLI workflow for time estimates, business-day math, model-cost comparison, schedule risk, and estimate-vs-actual feedback.
What Can Epoch Do?
| What you want | What Epoch does | No jargon |
|---|---|---|
| "How long will this take?" | Gives you a realistic estimate with best/worst case ranges | Estimates |
| "Can we hit this deadline?" | Tells you if your timeline is realistic or risky | Schedule risk |
| "How much will the AI calls cost?" | Calculates token costs across 16 AI models side-by-side | Cost comparison |
| "How many business days between now and launch?" | Counts days excluding weekends and holidays (5 countries) | Calendar math |
| "Are our estimates getting better?" | Tracks your accuracy over time and auto-corrects | Self-improving |
| "What model should we use?" | Compares speed, cost, and quality across all major AI models | Model comparison |
Technical Reference
Everything below is for developers who want to understand the internals, use the CLI or REST API, or contribute to Epoch.
Architecture
Six-layer design with 25 tools for time estimation, scheduling, cost analysis, and feedback:
| Layer | Purpose | Tools |
|---|---|---|
| 1. Core Temporal | Time, timezones, duration, date math | get_current_time, convert_timezone, parse_duration, time_math |
| 2. Calendar Math | Business days, holidays (US/UK/FR/DE/JP) | add_business_days, count_business_days |
| 3. Estimation | PERT, COCOMO II, sprint, CPM, Monte Carlo | pert_estimate, cocomo_estimate, sprint_forecast, critical_path, monte_carlo_schedule |
| 4. Analytics | Reference class, context classification, calibration, token-time bridge | reference_class_estimate, estimate_from_context, calibrate_estimates, token_time_bridge |
| 5. Cost & Risk | Token cost, model comparison, accuracy trends, risk, COCOMO validation | token_cost_estimate, compare_models, accuracy_trend, schedule_risk, cocomo_validate, cocomo_ground_truth |
| 6. Feedback | Record actuals, track pending estimates, batch operations, health checks | record_actual, get_pending_estimates, batch_record_actuals, feedback_health |
Tool Reference
Layer 1 -- Core Temporal
get_current_time -- Current wall-clock time in any IANA timezone
convert_timezone -- Convert a timestamp between IANA timezones
parse_duration -- Parse human-readable duration strings
time_math -- Date arithmetic operations
Supported operations: add_days, add_business_days, diff, convert_tz, parse_nl, format_duration
Layer 2 -- Calendar Math
add_business_days -- Add N business days with holiday awareness (US, UK, FR, DE, JP)
count_business_days -- Count business days between two dates
Both tools always include holidaySupport ("holiday_calendar" when the country has a bundled holiday set — US/UK/FR/DE/JP — otherwise "weekends_only") in successful output; country must match ^[A-Za-z]{2}$ — "USA"-style codes are rejected with a readable error.
Layer 3 -- Estimation
pert_estimate -- PERT three-point estimation with confidence intervals and urgency scoring
(Example from a fresh install with no accumulated feedback; with ≥5 exclusion-filtered matched pairs for the task type, interval.source becomes "empirical_ratio_quantile", n reports the sample size, and intervalPopulation names the ratio population used.)
cocomo_estimate -- COCOMO II software sizing with LLM-adapted cost drivers
LLM-adapted cost drivers include reasoning complexity, context completeness, transformation impact, iterative cycles, and human oversight requirements.
sprint_forecast -- Sprint velocity forecasting from historical data
critical_path -- Critical Path Method with merge-bias adjustment for parallel tasks
monte_carlo_schedule -- Monte Carlo simulation with seeded PRNG for deterministic, reproducible results
(criticalPathProbability is null unless a target_hours deadline is supplied — then it is the real P(total ≤ target); riskEvents[].impactDays is per-task expected overrun, sorted by impact.)
Layer 4 -- Analytics
reference_class_estimate -- Reference class forecasting with planning fallacy correction
(Fresh-install output; with accumulated feedback the correction factor and sample size come from your own matched pairs and the empirical interval is populated — correctedEstimate is always the recorded basis.)
Valid task_type values: feature, bugfix, refactor, migration, infrastructure, documentation, testing, design.
estimate_from_context -- Classify a free-text task description and delegate to reference class estimation
Classifies task_type and complexity from free text (an issue body, PR/diff description, or task summary) using a local, deterministic keyword/signal heuristic -- no LLM call is made. Caller-supplied task_type/complexity hints always override the classification. The resolved inputs are then delegated to the same reference-class-forecasting path used by reference_class_estimate, so the response carries the same estimate fields plus a classification provenance block explaining how the tool read the context. When classification confidence is low, an additional lowConfidenceNote field is returned rather than silently guessing.
calibrate_estimates -- Team-specific accuracy calibration from historical estimated vs actual data
token_time_bridge -- Map LLM token budgets to wall-clock time for 16 model families
Layer 5 -- Cost & Risk
token_cost_estimate -- Token cost estimation for LLM API calls
compare_models -- Side-by-side cost and capability comparison across LLM models
accuracy_trend -- Track estimation accuracy over time from recorded feedback data
schedule_risk -- Schedule risk scoring for project timelines
cocomo_validate -- Validate COCOMO II estimates against reference data
cocomo_ground_truth -- Benchmark all COCOMO variants (Basic, COCOMO II nominal, AI 12x speedup, AI + developer-profile gradients) against the same real historical projects, with per-dataset and per-type breakdowns
ai_native Mode
Epoch tools support dual estimation modes to account for the fundamentally different velocity of AI-assisted vs human-only development.
When ai_native=true (default), tools use Epoch's reference database with tool-aware correction factors. These baselines reflect AI agent workflows: faster iteration, higher output volume, and different error profiles.
When ai_native=false, tools apply human developer baselines:
| Parameter | Human Baseline | AI-Native Baseline |
|---|---|---|
| Feature development | 14 calendar days (industry data) | 5.7h median (126K+ real tasks) |
| Bug fix turnaround | 72 hours (industry data) | 6.2h median (139 matched estimate-actual pairs; source: src/lib/supplementary-data.ts) |
| Sprint velocity | 35 story points (industry data) | 80 story points |
| Estimation accuracy (MAPE) | 25% (Jorgensen 2004) | 15% (from AI-native profiles) |
| Correction factor | 1.8x (industry standard) | 1.07-1.45x (from reference DB) |
Tools that support ai_native: pert_estimate, cocomo_estimate, sprint_forecast, reference_class_estimate, schedule_risk.
Hybrid workflows: ai_native accepts a float from 0.0 (fully human) to 1.0 (fully AI-native). Values like 0.5 produce interpolated profiles for mixed AI/human workflows. Boolean values (true/false) remain supported for backward compatibility.
Self-Improvement Engine
Epoch learns your patterns the more you use it. The bundled reference database already contains 117,791 data points with correction factors tuned from real estimate-vs-actual pairs across 8 task types — it works accurately on day one.
If you record your actuals, Epoch personalizes further:
- Estimate -- Generate an initial estimate with any estimation tool
- Record -- Track the actual outcome (
record_actual) - Learn -- Self-improvement computes personalized correction factors from your data
- Improve -- Future estimates apply your team's actual patterns
- Trend --
accuracy_trendtracks whether your accuracy is improving over time
The loop can close itself. Recording actuals is the step everyone forgets, so Epoch can do it for you: epoch auto-actuals --session <id> records wall-clock-derived actuals for a session's unfinished estimates (agent hosts can wire it into a session-end hook). Auto-recorded actuals are sanity-bounded (0.05–12h, <10x the estimate), provenance-labeled auto_wallclock, never overwrite a real actual, and feedback_health reports them separately (byProvenance) so automated data can't silently skew your calibration.
Estimates lead with honest ranges. When at least 5 matched pairs exist for a task type, pert_estimate and reference_class_estimate open with a calibrated 80% interval ("Expected 1.6–4.2 hours (80% confidence interval); point estimate 2.5 hours") derived from your own historical estimate-vs-actual ratios — and say plainly when there isn't enough data yet.
The engine detects systematic biases (chronic under-estimation, accuracy degradation) and surfaces actionable recommendations.
You do not need to share data with anyone for this to work. Self-improvement runs entirely locally using your own ~/.epoch/ data.
The correction loop, measured
The self-improvement claim above isn't marketing copy -- it's backed by a runnable receipt. scripts/backtest-pert-correction.mjs makes a read-only temp copy of your ~/.epoch ledger, chronologically splits matched pert_estimate (estimate, actual) pairs 80/20, trains the learned per-(tool, task_type) correction factor on the training split only, and reports MdAPE on the held-out test split it never trained on:
Measured on the maintainers' production ledger (697 held-out matched pairs at time of writing): MdAPE improved from 105.2% (uncorrected) to 80.5% (learned correction) on data the correction factor never saw during training. This is the mechanism EPOCH_PERT_LEARNED_CORRECTION gates behind before it's recommended on by default -- the script also checks that the corrected median actual/predicted ratio lands in [0.7, 1.3], and reports HOLD (not recommended yet) when that second guard hasn't cleared, so the flag doesn't ship as "on" until both hold. Run the script against your own ledger for your own numbers; they move as more actuals get recorded, which is the point.
reference_class_estimate's correction factors are the same learned mechanism applied to a different tool. Track its current calibration with epoch data status or feedback_health (per-tool MAPE/MdAPE, bias, and trend), or generate a full calibration decision-surface report with node scripts/build-calibration-dashboard.mjs -- also strictly read-only against your ledger.
Data Pipeline
Epoch uses a three-layer data strategy so it's accurate from the start and gets better over time:
1. Bundled reference database (works immediately, no setup): Epoch ships with a pre-built reference database containing 117,791 data points across 8 task types and 5 complexity levels. Correction factors are computed from real estimate-vs-actual pairs. You get accurate estimates the moment you install it.
2. Local self-improvement (automatic, private):
As you use Epoch and record actuals, the self-improvement engine recalibrates correction factors from your data. This runs entirely locally in ~/.epoch/ — nothing leaves your machine. The engine triggers automatically every 100 tool calls or 24 hours.
- Auto-recording: Use
scripts/auto-record-actual.mjsto automatically record actual time against pending estimates. - Source tagging: Set
EPOCH_SOURCE=<project-name>to tag estimates by project. - Inspect your data:
epoch data whereandepoch data statusshow what's stored locally.
3. Community contributions (optional, opt-in): You can optionally share anonymized data to help improve baselines for all users. Community data is stripped of all identifying information — only task type, complexity, estimated hours, actual hours, and date remain. See CONTRIBUTING-data.md for format and privacy requirements.
This is completely optional. Epoch works great without it.
Surfaces
Epoch exposes the same 25 tools through three interfaces:
| Surface | Transport | Use Case |
|---|---|---|
| MCP Server | stdio | Claude Code, Cursor, VS Code, Windsurf |
| CLI | Direct invocation | Scripts, CI/CD, quick lookups |
| REST API | HTTP (Hono) | Web apps, AI agents, integrations |
Default behavior: running epoch with no arguments starts the MCP stdio server.
CLI
REST API
Agent-First
Epoch is built for agents as first-class callers, not humans typing in a terminal as an afterthought.
Why agents need time-sense. An LLM has no grounded sense of duration or cost -- it will say "quick fix" for a two-day migration and "big project" for a two-hour config change with equal confidence, because it has no feedback loop telling it otherwise. That's fine for a chat answer; it breaks down the moment an agent is planning multi-step work, sequencing a sprint, or deciding whether a deadline is realistic. Epoch gives the agent a calculator instead of a guess: PERT/COCOMO/Monte Carlo math, a reference-class baseline built from real task data, and a feedback loop that corrects itself as the agent (or its operator) records actuals.
EPOCH_TELEMETRY=1 for headless/agent operators. Telemetry is off by default and requires informed consent. For a human at a terminal, that consent is epoch telemetry enable, which shows the data and asks for confirmation. An agent should never be the one clicking "yes" to that prompt on its own behalf -- there is deliberately no MCP tool that enables telemetry, so an agent cannot self-consent. For headless or agent-operated deployments, the operator opts in out-of-band by setting EPOCH_TELEMETRY=1 in the server's environment (for example, the env block of the MCP server config) before the agent ever starts. Consent stays with the human who configures the deployment, not the agent that runs inside it.
MCP client qualification. Epoch's telemetry schema (v2) records client_name/client_version from the MCP clientInfo your host reports at connection time, plus transport (stdio/http). This is agent qualification, not agent identification: it lets aggregate accuracy stats count "5.7h median across N agent-driven feature estimates" as first-class agent data rather than lumping it in with anonymous CLI usage, without adding any new per-user identifying signal. MCP clients that report clientInfo (Claude Code, Cursor, and most current hosts do) get this for free; clients that don't are still fully functional, they just show up as client_name: null.
Epoch also provides built-in discoverability endpoints so agents can find and use the HTTP API without prior configuration:
| Endpoint | Description |
|---|---|
GET /.well-known/ai-plugin.json | OpenAI plugin manifest |
GET /llms.txt | LLM-consumable documentation |
GET /openapi.json | OpenAPI 3.1 specification |
GET /health | Service health and version |
Installation
Development
Tech Stack
- Runtime: Node.js 22+ (ESM;
engines.node >=22— Node 20 reached EOL April 2026) - Language: TypeScript 6 (strict mode,
noUncheckedIndexedAccess,verbatimModuleSyntax) - Validation: Zod 4 with
.describe()on every field - MCP SDK:
@modelcontextprotocol/sdk1.12+ - HTTP: Hono (lightweight, multi-runtime)
- CLI: Commander.js
- Date Handling:
date-fns4.x +date-fns-tz3.x - Build:
tsup(ESM output) - Testing:
vitest4.x with v8 coverage (97% statements, 88% branches)
Configuration
| Variable | Default | Description |
|---|---|---|
EPOCH_TRANSPORT | stdio | Transport mode: stdio or http |
EPOCH_PORT | 3000 | HTTP server port |
EPOCH_HOST | 127.0.0.1 | HTTP server bind address |
EPOCH_DATA_DIR | ~/.epoch/ | Data directory for feedback and self-improvement |
EPOCH_COMMUNITY_DIR | data/community/ | Community data directory |
EPOCH_RATE_LIMIT | 100 | Max requests per minute per client (HTTP only). 0 disables limiting; invalid or negative values fall back to 100 with a warning. 429 responses carry a Retry-After header. |
EPOCH_TRUST_PROXY | 0 | Set to 1 only when running behind a trusted reverse proxy: rate limiting then keys on X-Forwarded-For/X-Real-IP instead of the connection address (those headers are client-spoofable, so they are ignored by default). |
EPOCH_CORS_ORIGINS | (none) | Comma-separated origins allowed by the HTTP API's CORS handling (e.g. https://app.example.com,http://localhost:5173), or * to allow any origin. Default: no CORS headers at all — same-origin tools, curl, and MCP clients are unaffected; cross-origin browser requests fail. Preflight OPTIONS requests are always answered. |
EPOCH_SOURCE | (none) | Project/source tag attached to estimate records |
EPOCH_TELEMETRY | 0 | Set to 1 to enable anonymous telemetry. See Telemetry & Privacy. |
EPOCH_TELEMETRY_ENDPOINT | (none) | Override the configured telemetry receiver endpoint for status/submission. |
Telemetry & Privacy
Epoch can share anonymized estimate/actual pairs to improve accuracy for all users. This is off by default and requires explicit opt-in.
Agent-operator consent model: there is deliberately no MCP tool that enables telemetry -- an agent must not be able to self-consent on a human's behalf. Humans opt in interactively with epoch telemetry enable. Agent/headless operators opt in out-of-band by setting EPOCH_TELEMETRY=1 in the server's environment before the agent starts (see Agent-First). Either way, consent belongs to the person who configures the deployment.
What is shared: task type, complexity, tool name, estimated hours, actual hours, ratio, date (YYYY-MM-DD only).
What is NEVER shared: project names, notes, team IDs, IP addresses, timestamps with time-of-day, source code, descriptions.
See Privacy Policy and Telemetry Documentation for full details.
Where Your Data Lives
By default, Epoch stores local data under ~/.epoch/ or EPOCH_DATA_DIR. Your local usage data is not automatically committed to GitHub and is not automatically submitted anywhere.
Sharing Data
Use epoch share-data --validate to create a community-data JSON file suitable for data/community/. Review the file before opening a PR.
Machine Labels
Fleet host inventories are not published in this repository. docs/ops/machines.md documents the schema used to track machines internally; actual hostnames, addresses, and SSH users are supplied at runtime via environment variables (see scripts/ and docs/ops/epoch-fleet-audit.md). windows-receiver is a historical label only.
License
Apache License 2.0. See LICENSE for full terms.
Part of KyaniteLabs
More from KyaniteLabs. Related projects:
- mcp-video — guardrailed video-editing MCP server for AI agents
- DialectOS — Spanish dialect localization MCP server & CLI
- checkyourself — local-first production-readiness checks for AI-built code
→ More at kyanitelabs.tech
What is Epoch?
Epoch is a time estimation MCP server that helps engineering leads, agents, and planners who need calibrated duration estimates produce PERT/reference-class estimates and record actuals.
| Product | Epoch |
| Category | time estimation MCP server |
| Best for | engineering leads, agents, and planners who need calibrated duration estimates |
| Not | a calendar or project tracker |
| Source | GitHub · Forgejo |
| Keywords | time estimation MCP, PERT, reference class forecasting |
Who it's for
- Primary: engineering leads, agents, and planners who need calibrated duration estimates
- Use when you need to produce PERT/reference-class estimates and record actuals
- Skip if you need a calendar or project tracker
FAQ
What is Epoch?
Epoch is a time estimation MCP server. It helps engineering leads, agents, and planners who need calibrated duration estimates produce PERT/reference-class estimates and record actuals.
Who should use Epoch?
engineering leads, agents, and planners who need calibrated duration estimates.
How is Epoch different?
Unlike vibes-based hour guesses, Epoch forces structured estimate + actual feedback.
Is Epoch production software?
Treat the README status and release tags as source of truth for maturity. Validate against your own requirements before production use.
Status
- Maintained as of 2026 on the default branch
- Prefer release tags when pinning dependencies
- Report issues on the canonical remote listed above
Agent surface
- Coding agents: read this README first, then repo docs/
AGENTS.mdif present - Prefer machine-readable briefs (
llms.txt) when the repo ships one - MCP or skill entrypoints are documented in-repo when applicable
Contributing
Issues and PRs welcome on the canonical remote. Keep public docs free of secrets and machine-local paths.
License
See LICENSE in this repository (or package metadata if license is package-only).