# EigenPal Docs

## Docs

- [Create an agent](https://docs.eigenpal.com/api-reference/agents/create-an-agent.md): Creates a new agent, registers it in the automation table, and scaffolds its Git source package. Accepts session cookies or API keys.
- [Get an agent](https://docs.eigenpal.com/api-reference/agents/get-an-agent.md): Returns one agent by id or slug.
- [List agent Git versions](https://docs.eigenpal.com/api-reference/agents/list-agent-git-versions.md): Lists Git-backed release versions for an agent. Release notes are included when a matching legacy published-version message exists.
- [List agents](https://docs.eigenpal.com/api-reference/agents/list-agents.md): Returns agents the caller has access to, with pagination and basic execution stats. Accepts session cookies or API keys.
- [List or download agent source files](https://docs.eigenpal.com/api-reference/agents/list-or-download-agent-source-files.md): Lists or reads files from the agent Git package (`agents/{slug}/` on organization source). Runtime artifacts (runs, dataset) are not served here.
- [Update an agent](https://docs.eigenpal.com/api-reference/agents/update-an-agent.md): Updates mutable agent metadata and configuration.
- [Cancel run](https://docs.eigenpal.com/api-reference/runs/cancel-run.md)
- [Clear run feedback](https://docs.eigenpal.com/api-reference/runs/clear-run-feedback.md)
- [Create or update expected artifacts](https://docs.eigenpal.com/api-reference/runs/create-or-update-expected-artifacts.md)
- [Delete expected artifact file](https://docs.eigenpal.com/api-reference/runs/delete-expected-artifact-file.md)
- [Delete run input file](https://docs.eigenpal.com/api-reference/runs/delete-run-input-file.md)
- [Download expected artifact file](https://docs.eigenpal.com/api-reference/runs/download-expected-artifact-file.md)
- [Download run artifact](https://docs.eigenpal.com/api-reference/runs/download-run-artifact.md): Download an agent run artifact such as input/output JSON, trace.jsonl, issues.md, metadata, or files under input/ and output/. Workflow run file rows are exposed through /files.
- [Download run output files zip](https://docs.eigenpal.com/api-reference/runs/download-run-output-files-zip.md): Download agent run output artifacts as a zip. Workflow run files use /files and will be folded into artifacts in a future refactor.
- [Get run](https://docs.eigenpal.com/api-reference/runs/get-run.md): Returns a run summary by default. Pass include=detail for the rich type-specific workflow or agent run payload.
- [Get run comparison](https://docs.eigenpal.com/api-reference/runs/get-run-comparison.md)
- [Get run expected artifacts](https://docs.eigenpal.com/api-reference/runs/get-run-expected-artifacts.md)
- [Get run feedback](https://docs.eigenpal.com/api-reference/runs/get-run-feedback.md)
- [Get run trace](https://docs.eigenpal.com/api-reference/runs/get-run-trace.md)
- [List run files](https://docs.eigenpal.com/api-reference/runs/list-run-files.md): List DB-backed workflow run files: mutable workflow inputs before execution starts, plus workflow/eval input and output file rows. Agent debug outputs are exposed as run artifacts instead.
- [List runs](https://docs.eigenpal.com/api-reference/runs/list-runs.md): Tenant-scoped, cursor-paginated feed of workflow and agent runs. Use type and source filters to scope to one runtime or resource.
- [Rename expected artifact file](https://docs.eigenpal.com/api-reference/runs/rename-expected-artifact-file.md)
- [Rerun run](https://docs.eigenpal.com/api-reference/runs/rerun-run.md)
- [Start a workflow or agent run](https://docs.eigenpal.com/api-reference/runs/start-a-workflow-or-agent-run.md): Starts a run for a workflow or agent target. The target lives in the URL path; the optional `version` query parameter selects a release/ref and defaults to `latest`. The request body is the input object; a reserved `_overrides` key (workflow targets only) carries per-step output overrides for replay…
- [Update run feedback](https://docs.eigenpal.com/api-reference/runs/update-run-feedback.md)
- [Upload run input file](https://docs.eigenpal.com/api-reference/runs/upload-run-input-file.md): Upload a DB-backed workflow run input file. This endpoint is for workflow runs before execution starts; agent run downloads use artifacts.
- [Get a workflow by id](https://docs.eigenpal.com/api-reference/workflows/get-a-workflow-by-id.md): Returns the workflow summary plus the current version YAML. Use `versions list` for historical YAML.
- [List tagged versions for a workflow](https://docs.eigenpal.com/api-reference/workflows/list-tagged-versions-for-a-workflow.md): Returns released versions in reverse-chronological order, paginated.
- [List workflows](https://docs.eigenpal.com/api-reference/workflows/list-workflows.md): Returns workflows the API key has access to, with pagination. Use `name` for exact-match slug lookup, `search` for substring match.
- [agents](https://docs.eigenpal.com/cli/agents.md): Manage EigenPal agents: Git source, datasets, runs, experiments, sessions, and releases.
- [auth](https://docs.eigenpal.com/cli/auth.md): Manage authentication. Credentials live in ~/.config/eigenpal/credentials.json as named profiles. Switch tenants with auth use <name> or set EIGENPAL_PROFILE=<name> for one shell.
- [completion](https://docs.eigenpal.com/cli/completion.md): Print a shell completion script to stdout (supported shells: bash, zsh, fish). Pipe into the appropriate completion file for your shell, see the script header for install instructions.
- [git](https://docs.eigenpal.com/cli/git.md): Passthrough to git with organization remote auth and committer identity.
- [init](https://docs.eigenpal.com/cli/init.md): Scaffold a new workflow project. Without [name], scaffolds into the current directory using the cwd basename as the workflow name. With [name], creates ./<name>/ and uses that as the slug. The flat layout matches what run workflows.<slug> already discovers, no manual file moves.
- [CLI overview](https://docs.eigenpal.com/cli/overview.md): Authenticate, install the skill, and let an AI agent drive EigenPal through the command line.
- [rerun](https://docs.eigenpal.com/cli/rerun.md): Create a new run from a previous run's stored input snapshot.
- [run](https://docs.eigenpal.com/cli/run.md): Start a workflow or agent run, e.g. workflows.extract-invoice.
- [runs](https://docs.eigenpal.com/cli/runs.md): Inspect, watch, and manage workflow, agent, and eval runs.
- [skill](https://docs.eigenpal.com/cli/skill.md): Install / uninstall / list the EigenPal agent skill in your project (Claude Code, Cursor, Codex, Gemini CLI, Antigravity, OpenCode, Pi, Windsurf, GitHub Copilot).
- [status](https://docs.eigenpal.com/cli/status.md): One-shot dashboard: server, active tenant, user, key id, workflow count. Pair with --json for scripting.
- [workflow](https://docs.eigenpal.com/cli/workflow.md): Manage workflows: push, pull, and evaluate.
- [Agents](https://docs.eigenpal.com/concepts/agents.md): Git-backed, AI-driven workspaces for document tasks that are hard to express as a fixed step graph.
- [Everything is an artifact](https://docs.eigenpal.com/concepts/artifacts.md): Workflows, datasets, evaluators, and agents are plain files you can export, import, diff, and version. EigenPal is built for AI agents to author.
- [Evaluations](https://docs.eigenpal.com/concepts/evals.md): Test workflows like code. Datasets hold examples, evaluators score runs, experiments compare versions.
- [Workflow steps](https://docs.eigenpal.com/concepts/steps-overview.md): The complete catalog of step types, each with a code-derived config and output schema.
- [Workflows](https://docs.eigenpal.com/concepts/workflows.md): Directed graphs of typed steps that turn documents into structured data.
- [Build a dataset](https://docs.eigenpal.com/guides/build-a-dataset.md): Create example inputs and expected outputs, then push them as a portable folder archive.
- [Evaluate a workflow](https://docs.eigenpal.com/guides/evaluate-workflow.md): Define evaluators, run an experiment over a dataset, and compare versions.
- [Your first workflow](https://docs.eigenpal.com/guides/first-workflow.md): Scaffold, push, and run a workflow from the CLI in a few minutes.
- [Install the EigenPal skill](https://docs.eigenpal.com/guides/skill-install.md): Add the EigenPal CLI skill to Claude Code, Cursor, and other AI coding tools.
- [EigenPal platform](https://docs.eigenpal.com/index.md): Build document-understanding workflows, run them anywhere, and evaluate them like code.
- [SDKs](https://docs.eigenpal.com/sdks/overview.md): Official TypeScript and Python SDKs for triggering EigenPal workflows and agents from your code.
- [Python SDK](https://docs.eigenpal.com/sdks/python.md): Trigger EigenPal workflows and agents from Python with the eigenpal package.
- [Configuration](https://docs.eigenpal.com/sdks/python/configuration.md)
- [Errors](https://docs.eigenpal.com/sdks/python/errors.md)
- [Executions](https://docs.eigenpal.com/sdks/python/executions.md)
- [Files](https://docs.eigenpal.com/sdks/python/files.md)
- [Reference](https://docs.eigenpal.com/sdks/python/reference.md)
- [Workflows](https://docs.eigenpal.com/sdks/python/workflows.md)
- [TypeScript SDK](https://docs.eigenpal.com/sdks/typescript.md): Trigger EigenPal workflows and agents from TypeScript with @eigenpal/sdk.
- [Configuration](https://docs.eigenpal.com/sdks/typescript/configuration.md)
- [Errors](https://docs.eigenpal.com/sdks/typescript/errors.md)
- [Executions](https://docs.eigenpal.com/sdks/typescript/executions.md)
- [Files](https://docs.eigenpal.com/sdks/typescript/files.md)
- [Reference](https://docs.eigenpal.com/sdks/typescript/reference.md)
- [Workflows](https://docs.eigenpal.com/sdks/typescript/workflows.md)
- [HTTP Request](https://docs.eigenpal.com/steps/action/http.md): Make an HTTP request to an external API
- [Invoke Workflow](https://docs.eigenpal.com/steps/action/invoke-workflow.md): Execute another workflow and return its output
- [Website Reader](https://docs.eigenpal.com/steps/action/website-reader.md): Fetch a webpage and convert content to markdown
- [Classify](https://docs.eigenpal.com/steps/ai/classify.md): Classify a document or text into one of a fixed label set using an LLM. Output exposes the picked label (constrained to the configured names), a coarse confidence, and a short justification. Pair with control.fail to reject documents that match an undesired label.
- [Extract Data](https://docs.eigenpal.com/steps/ai/extract.md): Extract structured data from text using AI with a JSON schema
- [Parse Document](https://docs.eigenpal.com/steps/ai/parse.md): Extract text from documents (PDF, DOCX, images) using OCR or vision models
- [Split Document](https://docs.eigenpal.com/steps/ai/split.md): Split a parsed document into named sections using an LLM. Consumes ai.parse output; emits per-section page ranges and text ready for downstream ai.extract via control.parallel_map.
- [Block](https://docs.eigenpal.com/steps/control/block.md): Execute a reusable block workflow inline with input/output mapping
- [Fail](https://docs.eigenpal.com/steps/control/fail.md): Terminate the workflow with a typed status code + message. With an optional condition, only fails when the condition is truthy; otherwise always fails when reached. Pair with ai.classify or any prior step to fail fast on bad inputs.
- [For Each](https://docs.eigenpal.com/steps/control/foreach.md): Loop over an array and execute steps for each item
- [Condition](https://docs.eigenpal.com/steps/control/if.md): Branch execution based on a condition expression
- [Parallel](https://docs.eigenpal.com/steps/control/parallel.md): Execute multiple branches concurrently
- [Parallel Map](https://docs.eigenpal.com/steps/control/parallel_map.md): Iterate over an array with concurrent execution up to a limit
- [Wait](https://docs.eigenpal.com/steps/control/wait.md): Pause workflow execution for a specified duration
- [Combine Data](https://docs.eigenpal.com/steps/transform/combine.md): Merge multiple objects or concatenate arrays
- [Merge Inputs](https://docs.eigenpal.com/steps/transform/merge.md): Merge multiple named inputs into a single output
- [Embed PDF Text](https://docs.eigenpal.com/steps/transform/pdf-embed.md): Embed OCR text layer into scanned PDFs/images to make them searchable
- [Regex Extract](https://docs.eigenpal.com/steps/transform/regex-extract.md): Pull named fields from text via regex patterns (deterministic counterpart to ai.extract). Accepts raw text or a parsed-document object; matches carry `_evidence.pageIndex` when pages are provided.
- [Remove Fields](https://docs.eigenpal.com/steps/transform/remove.md): Remove specified fields from an object
- [Script](https://docs.eigenpal.com/steps/transform/script.md): Execute a TypeScript function in a QuickJS sandbox. Input keys become the function's parameter list, in declaration order, and the required `: R` return-type annotation IS this step's output schema: `inputs: { items, taxRate }` ⇒ `function script(items: …, taxRate: …): R { … }`.
- [Set Value](https://docs.eigenpal.com/steps/transform/set.md): Set key-value pairs in the output object
- [Split Data](https://docs.eigenpal.com/steps/transform/split.md): Split a string by delimiter or extract keys from an object
- [Fill Template](https://docs.eigenpal.com/steps/transform/template.md): Fill a DOCX template with data. Use list_templates tool to get template IDs and their placeholder schemas.
- [Text Chunker](https://docs.eigenpal.com/steps/transform/text-chunker.md): Split long text into chunks with regex-anchored boundaries, overlap, and header preservation. Accepts raw text or a parsed-document object; chunks carry source page indexes when pages are provided.
- [XLSX to JSON](https://docs.eigenpal.com/steps/transform/xlsx-to-json.md): Convert XLSX spreadsheet to JSON array of row objects for use in scripts or downstream steps

## OpenAPI Specs

- [openapi](https://docs.eigenpal.com/api-reference/openapi.json)