Agent Apprenticeship
Turn local agent task runs into reusable experience and runtime training.
- Source repo
- ray-r-ren/agent-apprenticeship
- Stars
- ★ 1.6k
- Last updated
- 2mo ago
- License
- MIT
- Primary language
- Python
- FA score
- 43/100 · Major gaps
At a glance
- Works with
- Universal · cross-platformCodex · Claude Code · OpenAI API · Claude API
- You'll need
- Typical use
- A developer using Codex locally wants to run a multi-step research or release-checklist task and reuse its resulting experience in later runs.
- Main limitation
- Requires a local shell, filesystem access, and an installed agent CLI; the documented flow is not a one-click hosted service.
- Source review
- 43/100 · Major gaps 1 safety controls not found
What does this agent do, and when should you use it?
Agent Apprenticeship is a local command-line workflow-loop system in which apprentice agents execute tasks with evaluation from mentor models, users, or human experts. It supports Codex, Cursor, Claude Code, OpenClaw, OpenCode, Hermes Agent, and custom command templates, and it detects installed CLIs. Completed runs print a local run folder and an Experience Compilation path; compilations can be inspected, checked, exported, searched, pulled, or installed as Runtime Training for later work. The project also documents Public Ecosystem and Private Internal Only contribution modes, plus a Seed Dataset v0.2 containing tasks, traces, and experience records.
apprentice run "<task>" starts a task workflow using the configured Apprentice Agent. apprentice configure and apprentice configure model configure the agent, mentor model provider, and Apprenticeship Mode; custom agents can be connected with apprentice configure agent custom --command-template "...". After a run, apprentice watch <run_id> follows progress, while apprentice ecosystem inspect <experience_compilation_path> and apprentice bundle check <experience_compilation_path> inspect the resulting Experience Compilation. apprentice ecosystem export ... --full exports the full compilation, and apprentice learn install ... installs prior experience as Runtime Training; public-mode commands also include apprentice ecosystem search, inspect, and pull.
- A developer using Codex locally wants to run a multi-step research or release-checklist task and reuse its resulting experience in later runs.
- An individual who has Claude Code, Cursor, or OpenCode installed needs to select one local CLI as the task executor.
- A team with an internal command-line agent wants to integrate it through a custom template using
{workspace}and{prompt_file}. - A domain-expert team wants an Expert-Led workflow where mentor models, users, or human experts participate in real task completion.
- A user needs to audit or reuse prior task output by inspecting, exporting, searching, or pulling Experience Compilations.
How do you install or deploy this agent?
A working Node.js and npm installation, plus the local agent CLI you intend to use, are required. Run:
npx agent-apprenticeship initOr install globally:
npm install -g agent-apprenticeship
apprentice initFor mentor model providers, configure the applicable OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, or OPENROUTER_API_KEY in ~/.agent-apprenticeship/.env.local; the same variables may instead be set for the current shell session. Run apprentice doctor to check setup.
How do you use this agent?
After initialization, run apprentice configure, or use apprentice configure model for the mentor provider, then review settings with apprentice settings. A first task can be started with:
apprentice run "Create a short market map for AI procurement tools."Use apprentice watch <run_id> to monitor it. When it finishes, inspect the emitted Experience Compilation path with apprentice ecosystem inspect <experience_compilation_path>; optionally run apprentice learn install <experience_compilation_path> before a future task. For a session-only loop limit, set AA_MAX_ITERATIONS=3.
What are this agent's strengths and limitations?
- Supports several local agent CLIs in one workflow system and provides a documented custom command-template path.
- Treats completed work as an Experience Compilation that can be checked, fully exported, searched, pulled, and later installed.
- Documents Autonomous, Expert-Led, and Organization Custom Apprenticeship Modes.
- Publishes Seed Dataset v0.2 with 500+ seed tasks, 1,000+ full execution traces, and 505 full experience compilations.
- Requires a local shell, filesystem access, and an installed agent CLI; the documented flow is not a one-click hosted service.
- Mentor configuration depends on API keys for OpenAI, Anthropic, Gemini, or OpenRouter; model pricing and billing are not specified.
- Loop depth must be managed through settings or
AA_MAX_ITERATIONS; no automatic failure-recovery behavior is documented. - The supplied material does not specify collaboration permissions, data redaction, or a review process before contributing to the public ecosystem.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|
| Agent Apprenticeship This agent | 43 · Major gaps | ★ 1.6k | 2mo ago | Python | Codex · Claude Code · OpenAI API · Claude API |
| Agent Toolkit | 74 · Some gaps | ★ 18 | 3d ago | V | ChatGPT · Codex · Claude Code |
| GameDesignOS: A Local-First Operating System for AI-Assisted Game Design | 78 · Good | ★ 395 | 1mo ago | Python | Codex · Claude Code |
| OmniGet Desktop Agents & Downloader | 71 · Some gaps | ★ 14k | 1d ago | Rust | Codex · Claude Code · OpenAI API · Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence: README mentions storing API keys in ~/.agent-apprenticeship/.env.local and supports public/private modes, but does not specify least privilege or user confirmation mechanisms. Data flow transparency is limited, with no detailed explanation of how data is collected, used, and shared. Sensitive data handling only mentions key storage, without encryption or protection details. Dependency security does not mention vulnerability scanning or locking. External effects are not clearly specified regarding network calls or data uploads. Rollback mechanism is absent. Source attribution is not clearly defined for data sources or contributors. Deductions: lack of specific implementation details and evidence.
Evidence: README and package.json commands and descriptions are largely consistent, but no test results or runtime evidence are provided. Dependency availability is not explicitly stated, but dependencies are listed. Failure messages are not mentioned regarding error handling or user prompts. Deductions: static review cannot verify runtime behavior, and documentation lacks failure handling details.
Evidence: README clearly lists target users (local agent users) and scenarios (workflow loops, cross-domain tasks). Capability boundaries are not explicitly defined, but multiple agents and modes are mentioned. Trigger precision is not detailed for command parameters. Environment fit mentions Node >=18 and Python >=3.11, but OS compatibility is not specified. Deductions: capability boundaries and trigger precision are insufficiently described.
Evidence: README provides installation, quickstart, and command descriptions with clear structure. Install notes are detailed, including npx and global installation. Naming stability: two command names (apprentice and agent-apprenticeship) are provided, but version compatibility is not explained. Examples and FAQ have basic examples but no FAQ. Known limitations are not mentioned. License is MIT, version exists, but no changelog. Maintenance responsibility is not clear. Deductions: missing known limitations, changelog, and maintenance responsibility.
Evidence: Output usability: provides run result paths and inspection commands. Marginal value: emphasizes economic value and reusable experience, but not quantified. Cost-benefit: no mention of resource consumption or costs. Deductions: cost-benefit lacks specific data.
Evidence: Claims in README (e.g., dataset sizes) lack verification methods. Cross-source corroboration: only mentions Hugging Face dataset, no other sources. Fact-inference separation: does not clearly distinguish facts from inferences. Deductions: lack of verifiable evidence and sources.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- API key storage and permission management need further review to ensure least privilege.
- Data flow and sharing mechanisms are opaque; clarify data collection, use, and sharing policies.
- Dependency security is not mentioned; check dependency versions and security.
- Rollback mechanism is absent; consider failure recovery options.
- Claims in documentation (e.g., dataset sizes) lack verification methods; treat with caution.
FAQ
Which agents can it run directly?
Must experience be contributed publicly?
Public Ecosystem and Private Internal Only modes.What credentials are needed for mentor models?
How is one task's output reused?
apprentice learn install <experience_compilation_path> before future work.What checks are available when setup or output has problems?
apprentice doctor for setup checks and apprentice bundle check <experience_compilation_path> for an Experience Compilation.