CLI-first time-series automation for enterprise and research AI.
2026-05-13
CLI + workflows + skills + sandboxes for reproducible time-series automation.
workflow
Reproducible end-to-end runs
tool
Direct access to analysis functions
skills
Domain runbooks for agent harnesses
sandbox
Isolation for messy dependencies
Why automate the work?
Why make it a CLI?
Agent or script
Codex / Claude / LangChain / CI
plans and runs
ts-agents
workflow · tool · skills · sandbox
writes
Artifacts
JSON · PNG · CSV · Markdown · manifests
The CLI is intentionally the stable spine. Agents, scripts, notebooks, and CI can all call the same contract.
What happens
window_scores.png
confusion_matrix.png
report.md
What happens
forecast_comparison.png
forecast.csv
report.md
Workflow reports
Each first-class workflow writes a short Markdown report alongside structured outputs.
ts-agents workflow run forecast-series --output-dir outputs/forecast
report.md
run_manifest.json
forecast.csv
Stakeholder reports
A report-generation skill can turn a run manifest and artifacts into a Quarto or PDF report.
ts-agents skills show report-generation
quarto render outputs/reports/forecast.qmd
The interaction can be conversational, scheduled, or scripted. The deliverable is the artifact bundle.
Start with mature CLI agents
They already provide repo search, command execution, logs, diffs, permissions, background jobs, and resumable sessions.
Inject domain expertise with skills
SKILL.md files encode tool order, cheap baselines, artifact checks, report expectations, and done criteria.
Custom agents are still possible
Build a dedicated harness when you need proprietary integrations, strict policies, non-developer workflows, or offline/low-latency deployment.
The practical path is incremental: stable CLI first, skills next, custom harness only when the use case justifies it.
Pain point
When many similar tools exist, agents often jump to expensive or fragile methods before checking cheap baselines.
How ts-agents helps
Tool metadata, bundles, and skills make the intended order explicit: cheap baselines, robust defaults, then advanced methods.
This matters for forecasting, classification, anomaly detection, and any workflow with multiple plausible algorithms.
Pain point
Minutes-to-hours jobs need progress, logs, retry behavior, review checkpoints, and resumable state.
How ts-agents helps
Run-scoped output directories, manifests, artifact refs, cost metadata, and sandbox hooks make jobs batch-friendly.
The roadmap is to push this further: progress reporting, checkpoint recovery, and richer run history on top of the current background-job and run-catalog surfaces.
Pain point
Time-series stacks are fragmented: optional libraries, compiled dependencies, version conflicts, and cloud/local differences.
How ts-agents helps
Keep imports lazy, detect install profiles, and use sandbox backends for isolation, reproducibility, and heavier workloads.
Sandboxes are not magic: data gravity, cold starts, cost governance, and infrastructure debugging still matter.
Stable surfaces
capabilities, workflow show, strict JSON envelopes, typed artifacts
Demo-ready workflows
Inspection, forecasting, activity recognition
Agent-friendly outputs
Run manifests, non-clobbering output dirs, artifact refs
Integration paths
External framework tool wrappers, packaged skills, mature CLI agents
Process industry
Supplement simulation forecasts, scan sensor fields, flag anomalies, and summarize operating regimes.
Live or batched data
Run scheduled diagnostics, forecast refreshes, quality checks, and report generation over streaming or daily batch data.
Research teams
Compare experiments with repeatable commands, preserve artifact trails, and turn repeated analyses into reusable skills.
Custom harnesses
Use ts-agents as one callable subsystem inside a larger orchestrator with governance, data access, and review.
Policy gradient
Learns inside the policy.
Autoresearch
Learns through artifacts and workflow changes.
Simple examples
Policy gradient: sample workflow choices, reward lower validation RMSE, then update orchestrator weights toward actions that picked better methods.
Autoresearch: Iteration 0 finds Theta wins on metrics, but the figure shows drift and the report flags short validation. Iteration 1 runs decomposition, widens baselines, and updates the forecasting skill.
Autoresearch can improve the orchestrator, but also the surrounding skill files, tool metadata, eval rubrics, and reusable workflow defaults.
What the agent remembers
Where ts-agents fits
ts-agents turns remembered preferences into repeatable workflow commands and artifact checksThe personal agent learns the user’s data-science playbook; ts-agents keeps each run auditable and reproducible.
Use the CLI as the durable contract across agents, scripts, and CI.
Treat artifacts as the product: plots, JSON, CSV, reports, and manifests.
Pair skills with memory so personalized agents choose methods, checks, and reporting style consistently.
Closing thought: ts-agents is strongest as a specialist subsystem inside a larger governed agent workflow.
Open source repo
Docs, examples, skills, and demo scripts are in the repository.
ts-agents