AI can write code.
But it can't tell time.
Epoch gives AI agents the ability to estimate timelines, calculate costs, and predict deadlines — with one command.
The problem no one is solving
AI agents are incredibly powerful. They write code, debug systems, and automate workflows. But ask them "how long will this take?" and they guess — badly.
Your AI agent confidently says "this will take 2 hours." Two days later, you're still waiting.
Large language models have no concept of time. Positional encodings represent token sequence position, not real-world duration. Self-attention provably cannot model counting behaviors.
- AI agents estimate in token budgets, not minutes
- Events 10 tokens apart have identical encodings whether 1 second or 1 hour apart
- LLMs replicate and amplify human optimism bias through agentic overconfidence
Epoch gives AI grounded estimates using 40+ years of software engineering research, packaged into 24 tools any AI can call.
Instead of hallucinating timelines, your agent calls a function. The function returns a data-driven estimate built on COCOMO II, PERT analysis, reference class forecasting, and Monte Carlo simulation.
- Structured external tools — not prompt hacks
- 24 MCP tools covering time, dates, estimation, analytics, and cost
- One command to install. Works with Claude, Cursor, VS Code, and any MCP client
Research-backed: A UPenn negotiation study showed 4% deal closure under wall-clock time limits vs 99% under turn-based limits. Injecting explicit time state into prompts produced an 8x improvement in negotiation outcomes. Epoch makes time legible to LLMs through structured external tools.
See it in action
A real interaction. No cherry-picking, no edits.
How long will a 15K LOC project take with a team of 5?
Based on COCOMO II estimation:
Confidence: 72% | Method: COCOMO II + PERT blend
5 layers of temporal intelligence
From basic time operations to Monte Carlo simulation. Each layer builds on the last, giving your AI progressively deeper temporal reasoning.
Time & Dates
Current time in any timezone, timezone conversion, duration parsing, date arithmetic
Business Days & Holidays
Working day calculations, holiday awareness (US, UK, FR, DE, JP), urgency classification
How Long Will It Take?
PERT three-point estimation, COCOMO II (LLM-adapted), sprint velocity, critical path method
Getting Better Over Time
Reference class forecasting, estimation accuracy tracking, historical data calibration
Cost & Risk
Monte Carlo simulation, token-to-time bridge, planning fallacy correction, team velocity calibration
What people are saying
Early adopters are using Epoch to give their AI agents temporal superpowers.
"We went from AI estimates that were off by 10x to estimates backed by real data. Epoch changed how our entire team plans sprints."
"The Monte Carlo simulation alone is worth it. Our PM team finally trusts the AI's deadline predictions."
"This is the right approach. External tools with grounded data, not prompt engineering. Epoch is how AI time estimation should work."
Testimonials are illustrative. Have a story? Share it on GitHub.
All 24 tools, one API
Zod-validated schemas, .describe() on every field, readOnlyHint annotations. Accessible through MCP, CLI, and REST.
| Tool | Description |
|---|---|
| get_current_time | Current time in any IANA timezone |
| convert_timezone | Convert ISO-8601 between timezones |
| parse_duration | Parse "2h30m" into structured seconds |
| time_math | 6 operations: add_days, diff, format_duration, add_hours, add_minutes, add_weeks |
| add_business_days | Add N working days, skipping weekends and holidays (5 countries) |
| count_business_days | Count working days between two dates |
| pert_estimate | Three-point PERT Beta distribution: E = (O+4M+P)/6 |
| cocomo_estimate | COCOMO II with 5 LLM-adapted cost drivers |
| sprint_forecast | Sprint velocity forecasting with variance-based pessimistic estimate |
| critical_path | CPM with forward/backward pass and merge bias |
| monte_carlo_schedule | Monte Carlo simulation with seeded PRNG, P10-P95 percentiles |
| reference_class_estimate | Reference class forecasting with industry correction factors |
| calibrate_estimates | Team-specific correction factor calibration from historical data |
| token_time_bridge | Map token budgets to wall-clock time for 12 LLM models |
| token_cost_estimate | Token cost estimation with input/output breakdown |
| compare_models | Side-by-side comparison across 12 LLM models |
| accuracy_trend | Sliding-window MAPE tracking over time |
| schedule_risk | Confidence intervals using team MdAPE |
| record_actual | Submit actual hours for a previous estimate |
| feedback_health | Comprehensive feedback data quality report |
Gets better the more you use it
Every estimate generates a feedback token. Record actual hours and Epoch auto-calibrates correction factors across task types, complexity levels, and tools.
Transparent by Design
Every data point is documented. Every record is anonymized. Telemetry is off by default.
Off by Default
Telemetry requires explicit opt-in. Preview exactly what will be shared before enabling.
Zero PII
No names, emails, project names, or company data. Dates truncated to day-only.
Self-Hostable
Configurable endpoint. Run your own telemetry server. Full API contract documented.
Three surfaces, one API
All 24 tools are accessible through MCP, CLI, and REST API. Use whichever fits your workflow.
MCP Server
Stdio transport for Claude Code, Cursor, VS Code
CLI
Scriptable subcommands with JSON or table output
REST API
HTTP server with OpenAPI spec and AI discoverability
Up and running in 30 seconds
No config files. No API keys. One command.
Install Epoch
Ask any time question
"What's the PERT estimate for a 3-month sprint?"
"How many business days until March 15?"
Get grounded, data-driven estimates
{
effort: "45 person-months",
duration: "8.3 months",
risk: "medium",
confidence: "72%"
}
That's it. Three steps.
View on GitHub