Runnable Examples
Complete Framework programs, maintained and compiled with the everruns crate.
The crates/everruns/examples catalog
contains the maintained public examples. Each imports the everruns facade.
Complete agents
Section titled “Complete agents”The root-level examples
catalog contains eight Framework walkthroughs. Each folder includes the program,
instructions, fixtures where applicable, and recording scripts. Run them from a
repository checkout: their dependencies point to the workspace crates.
cargo run uses a real provider and can incur charges. CI tests offline tool
behavior and recording logic; it does not establish the quality of a live model’s answer.
| Example | Provider and model | What it does |
|---|---|---|
| Support Agent | OpenAI gpt-6.2-sol |
Chooses between MFA recovery, lockout, and browser troubleshooting from facts and policy. |
| Everruns Support Agent | Anthropic claude-opus-5-5 |
Searches and reads citable official documentation snapshots. |
| Coding Review Agent | Anthropic claude-sonnet-5 |
Reads a refund contract and executes a fixed regression before reporting a defect. |
| Research Agent | OpenRouter z-ai/glm-5.2 |
Searches and fetches primary sources before writing a cited brief. |
| Incident Commander Agent | Meta Model API muse-spark-1.3 |
Investigates fixture telemetry and persists an evidence-backed incident update. |
Start with Support for typed tools, Research for reusable capabilities, or Code Review for restricted execution. Each walkthrough shows the agent builder and session loop, explains expected behavior, and documents what remains a fixture.
These are in-memory sessions. For durability itself, use the session-history and
workspace examples below. Importable hosted Platform definitions live separately
as TOML folders in examples/agents.
See file-based agents for loading, importing and serving them.
Execution runtimes
Section titled “Execution runtimes”| Example | Provider and model | What it does |
|---|---|---|
| Bashkit Repo Agent | OpenAI gpt-6.2-sol |
Cuts a release in a real repository with the sandboxed Bashkit shell as its only tool, then verifies the result on disk. |
| Code Mode MCP Agent | OpenAI gpt-6.2-sol (or through OpenRouter) |
Answers a question over a 1,000-tool MCP server by calling its tools from Bashkit scripts, with none of their schemas in the prompt. |
| Host Shell Agent | OpenAI gpt-6.2-sol |
Fixes a failing Rust test suite by compiling and running it through real processes inside a kernel-enforced boundary. |
| Foreman | TypeSafe jev-latest over an Everruns session, Codex, or yolop |
Supervises a live coding session with nine decision questions per reading, and stops, verifies, or finishes it from a deterministic policy. |
Terminal hosts
Section titled “Terminal hosts”| Example | Provider and model | What it does |
|---|---|---|
attached-cli |
OpenAI gpt-6.2-sol |
Serves a running session to a second terminal, which lists, watches, sends to and cancels it through attached control. |
Talking to other companies’ agents
Section titled “Talking to other companies’ agents”| Example | Provider and model | What it does |
|---|---|---|
poppy-personal-agent |
OpenAI gpt-6.2-sol |
Acts as a person’s own agent over the Personal Agent Protocol: finds a company by its domain, asks its agent about an order, and reports the answer. |
Serving agents
Section titled “Serving agents”These run agents as HTTP services with Serve.
| Example | What it does | Command |
|---|---|---|
serve/hello |
The smallest serve app: one agent, one tool | cargo run -p serve-example-hello |
serve/ag-ui |
An agent streamed to CopilotKit or any AG-UI client | cargo run -p serve-example-ag-ui |
serve/a2a |
Two agents over A2A: a researcher served by serve, and a writer that delegates to it. Offline by default | cargo run -p serve-example-a2a --bin researcher, then --bin writer -- "tide pools" |
serve/voice |
A hotel front desk people call from the browser, with a greeting and a speaking style | OPENAI_API_KEY=… cargo run -p serve-example-voice |
Durable hosts
Section titled “Durable hosts”Durable multiplayer chat on Cloudflare runs the portable kernel inside a SQLite-backed Durable Object, with shared rooms, forks, scheduled follow-ups, and a recoverable history-search child. This is an experimental advanced host example.
Core crate catalog
Section titled “Core crate catalog”| Example | Demonstrates | Command |
|---|---|---|
capability_configuration.rs |
Typed Compaction and ToolSearch, a code-defined Definition, and a dynamic third-party reference through one entrypoint | cargo run -p everruns --example capability_configuration |
model_catalog.rs |
Listing a provider’s models, reading their metadata, and running the selection | cargo run -p everruns --example model_catalog |
ask_user.rs |
Structured questions answered by a host responder, and the unattended defaults path, fully offline | cargo run -p everruns --example ask_user |
ag_ui_axum.rs |
An AG-UI 1.0 run served over axum | cargo run -p everruns --features ag-ui-axum --example ag_ui_axum |
image_generation.rs |
An agent on GPT-6.2 Sol that draws an animated GIF with GPT Image 2.6 Flare and saves it next to you | OPENAI_API_KEY=… cargo run -p everruns --features openai,images,local --example image_generation |
workspace_policy.rs |
Safe workspace scopes and trusted starter files, fully offline | cargo run -p everruns --example workspace_policy |
direct_llm.rs |
One-shot, builder, and streamed model calls with no agent, fully offline | cargo run -p everruns --example direct_llm |
direct_decisions.rs |
Typed questions and calibrated answers with no agent, fully offline | cargo run -p everruns --example direct_decisions |
agent_decisions.rs |
An agent that classifies with its own questions, offline by default | cargo run -p everruns --example agent_decisions |
live_session.rs |
Non-blocking send, automatic steering, and optional waiting, fully offline | cargo run -p everruns --example live_session |
hello.rs |
Small live-provider agent | cargo run -p everruns --features openai --example hello |
production_agent.rs |
Tools, files, and production-style setup | cargo run -p everruns --features openai --example production_agent |
github_monitor.rs |
Typed tools and an offline simulation mode | cargo run -p everruns --features openai --example github_monitor -- --simulate |
session_work.rs |
Offline session work, leased delivery, and completion wakes | cargo run -p everruns --example session_work |
session_history.rs |
Offline durable resume and bounded history pages | cargo run -p everruns --features local --example session_history |
engine_sessions.rs |
Concrete Engine ownership, isolated sessions, and engine-scoped resume | cargo run -p everruns --example engine_sessions |
workspace_heads.rs |
Isolated Git workspace heads, Environment binding, and durable reopening | cargo run -p everruns --features local --example workspace_heads -- /path/to/repo /path/to/state |
canonical_events.rs |
Offline bounded recording and typed rendering of live events | cargo run -p everruns --example canonical_events |
explicit_communication.rs |
Offline agent with explicit communication: sent messages apart from working notes | cargo run -p everruns --example explicit_communication |
framework_observability.rs |
Engine-wide OpenTelemetry and optional Braintrust export with explicit shutdown flushing | cargo run -p everruns --features otel,braintrust --example framework_observability |
subagents.rs |
Public facade composition for delegated work | cargo run -p everruns --features openai --example subagents |
observe_and_cancel.rs |
Live events and cancellation | cargo run -p everruns --features openai --example observe_and_cancel |
advanced_capability.rs |
Code-defined capability through the unified capability(...) entrypoint |
cargo run -p everruns --features openai --example advanced_capability |
lifecycle_hooks.rs |
Awaited agent, turn, tool, and completion handlers | cargo run -p everruns --features openai --example lifecycle_hooks |
Live-provider modes use gpt-6.2-sol and require OPENAI_API_KEY.
capability_configuration, canonical_events, direct_llm,
engine_sessions, explicit_communication, live_session, session_work, workspace_heads,
workspace_policy, and session_history are fully offline;
the GitHub monitor also offers a simulated GitHub flow:
cargo run -p everruns --features openai --example github_monitor -- --simulateFor copyable command details and behavior notes, use the example catalog next to the source. Examples that demonstrate low-level host internals remain advanced-host examples, not alternative Framework entrypoints.
Provider-native batches
Section titled “Provider-native batches”The batch guide shows offline work through Anthropic, OpenAI, Gemini, Mistral, Groq and Fireworks. Set BATCH_PROVIDER to the provider name, enable its Cargo feature and configure its API key. Both examples can incur charges.
| Example | Behavior | Run |
|---|---|---|
batch_classification.rs |
Persist submission intent and ticket; resume classification, collect or cancel where supported | cargo run -p everruns --features anthropic --example batch_classification -- submit /tmp/reviews-001 |
batch_eval.rs |
Submit typed message lists, poll and score three eval cases | cargo run -p everruns --features anthropic --example batch_eval |
Custom platform workers
Section titled “Custom platform workers”The Custom Data Agent Worker packages a Framework agent with private SQLite tools behind the restricted Platform worker protocol. Its complete smoke runner uses a real model, the ordinary session APIs and SSE, and checks replica replacement and credential rotation. This advanced host example needs a self-hosted CP; its shared history lives there.
The batch examples also accept BATCH_PROVIDER=mistral, groq or fireworks
with the matching Cargo feature. Fireworks requires account and artifact-origin
configuration; see Batch Model Requests.
Native GitHub PR review
Section titled “Native GitHub PR review”github_review.rs
reads a real PR with the native GitHub capability and prints an evidence-based
review. It requires OPENAI_API_KEY and GITHUB_TOKEN and does not write to GitHub.
See GitHub tools.
cargo run -p everruns --features github,openai --example github_review -- OWNER/REPO NUMBERApplication services
Section titled “Application services”| Example | Required features | What it runs |
|---|---|---|
| OAuth MCP | openai,mcp-auth |
Browser login, callback validation, authenticated MCP tool use |
| Slack actions | openai,slack-actions |
React and upload into one authorized thread |
| Data services | openai,sql-database,knowledge |
Retrieve policy, retain a SQL decision and write named memory |
| Native services | openai,cursor,browserless,e2b |
Use one selected vendor with explicit credentials and resource cleanup |
| Event triggers | openai,local,triggers |
Recoverable event dispatch and duplicate suppression across restarts |
| Evaluation and traces | openai,evaluation |
Run real cases, print scores and project canonical trace events |
Every example uses a real model and reports failed turns. See Application services for configuration and host responsibilities.