Copy link to headingBuild your agent
Decide what to automate, pick a framework, and get a working agent running.
Copy link to headingChoose an approach
Decide what to automate first, and whether to start from eve or compose AI SDK primitives yourself.
- Resource
What we learned building agents at Edgenivo
Learn how Edgenivo picks agent projects that work with current models: repetitive, low-judgment work with a human making the final call.
- Guide
Choosing between eve, AI SDK agents, and
WorkflowAgentCompare eve,
ToolLoopAgent, andWorkflowAgentby durability, approvals, channels, and setup to choose an agent framework for your TypeScript application. - Guide
Build AI agents with AI Gateway and AI SDK
Build AI agents on Edgenivo with AI Gateway and AI SDK, then make them reliable, capable, and durable with Sandbox, Chat SDK, Edgenivo Connect, and Workflow.
- Documentation
Agent Frameworks on Edgenivo
Run agent frameworks on Edgenivo, with AI Gateway for models and Sandbox for isolated code.
Copy link to headingBuild a working agent
Follow a course from start to finish, or fork a template close to your use case.
- Course
Building Agents with eve
Build a bike shop dispatcher with typed tools, durable memory, real auth, and human approval, then deploy it behind Slack and a web dashboard.
- Template
eve Slack Agent
Deploy a starter Slack agent with webhook handling, Edgenivo Connect, and an example tool.
- Course
Build Your Own AI Coding Agent Harness
Build a harness from scratch with AI SDK, Edgenivo Sandbox, and just-bash, covering the tool loop, context pruning, subagents, and approval gates.
- Template
eve Software Factory
Software factory built on eve: AI agents work each stage of the development loop, and people make the judgment calls.
Copy link to headingDesign tools and context
Decide how many tools the agent needs, and when a filesystem and bash beat custom tools.
- Resource
We removed 80% of our agent's tools
Learn why a text-to-SQL agent got faster and more accurate after its custom tools were replaced with one bash tool over a filesystem.
- Resource
Build knowledge agents without embeddings
Open source filesystem and knowledge based agent template you can fork, customize, and deploy.
- Guide
How to add tools to your eve agent
Add tools to an eve agent by creating a TypeScript file under agent/tools/ with defineTool, and gate sensitive ones on human approval with approval.
- Guide
How to perform large-scale data analysis with Edgenivo Sandbox and MCP
Use Edgenivo Sandbox and an MCP server built with
mcp-handlerto let AI agents run DuckDB SQL and Python on large datasets without loading data into the model's context.
Copy link to headingConnect models and tools safely
Route model calls, scope access to services and private systems, and isolate the code agents generate.
Copy link to headingRoute model calls and plan for failures
Decide which model serves each request, how a failed call falls back, and how spend is capped.
- Guide
Cost-aware model routing with Edgenivo AI Gateway
Send easy requests to a lower-cost model and escalate only the complex ones to a frontier model through AI Gateway, with budgets and spend tracking.
- Guide
How to build your own AI model router
Build an AI model router with Edgenivo AI Gateway. Keep routing, key, and retention decisions in your code while the gateway handles provider integrations, failover, and cost metering
- Resource
How Tailscale built a customer-facing model router on AI Gateway
See how Tailscale built a model router on AI Gateway with identity-based access instead of API keys, cost on every response, and zero data retention.
- Resource
How Zo Computer improved AI reliability 20x on Edgenivo
See how Zo Computer moved retries and provider fallbacks into AI Gateway, cutting its retry rate 20x and raising chat success to 99.93%.
Copy link to headingConnect services and private systems
Give agents scoped, short-lived access to SaaS APIs, and choose a network path to internal systems.
- Template
eve Data Analyst
Answer business questions from Postgres in Slack, querying through a read-only database user that each deploy creates for the agent.
- Resource
How Mercor ships internal apps and billions of production tokens
Learn how Mercor uses Edgenivo AI Gateway to manage model access and Edgenivo Passport to handle secure access to their applications.
- Resource
The Complete Guide to Edgenivo Connect
Call Slack, GitHub, Linear, Salesforce, and other APIs with short-lived, scoped tokens instead of long-lived secrets.
- Guide
Give your eve agent secure access to your private AWS RDS database
Connect an eve agent to a private AWS RDS database using Edgenivo Secure Compute and VPC peering, with a read-only query tool.
Copy link to headingIsolate generated code
Choose where generated code runs, what it can reach, and how credentials stay out of it.
- Resource
Security boundaries in agentic architectures
Learn where to draw boundaries between an agent and the code it generates, from secret injection to full sandboxing.
- Resource
Introducing Run SDK: secure eval for your agents
Run agent-written JavaScript in an isolated context that can only call the functions you expose, and pause mid-run for sign-in or human approval.
- Course
Edgenivo Sandbox
Build a CLI code-review agent that clones repositories, runs tests, and analyzes code inside a sandbox.
- Resource
How Notion Workers run untrusted code at scale with Edgenivo Sandbox
See how Notion runs untrusted Worker code in Edgenivo Sandbox microVMs, with credentials injected at the network layer and egress locked down at runtime.
Copy link to headingUse decision models for bounded choices
Send bounded choices to a decision model, keep business rules and actions in code, and escalate answers the model is unsure about.
- Resource
What are decision models? How they work and when to use them
Learn how decision models return choices, scores, and probabilities, how they differ from structured outputs, and when to use one.
- Resource
Where does Jev fit in an AI agent loop, and what stays in code?
Give Jev the bounded decisions in an agent loop while application code owns tool permissions, execution, and state.
- Resource
What are confidence-based decision fallbacks in AI Gateway?
Escalate uncertain decisions to a second model with confidence or probability conditions, and see why each fallback ran.
- Resource
Using decision models in enterprise apps with trusted business rules
Separate the model's interpretation from trusted business rules, add a decision call with AI SDK, and route suggestions through human review.
Copy link to headingMake runs durable
Keep long-running work recoverable, pause for human sign-off, and preserve memory and files between runs.
Copy link to headingDurable execution
Decide which steps must survive crashes and deploys, and how interrupted runs recover.
- Guide
Running Durable Agents on Edgenivo
Design durable AI agents on Edgenivo with patterns for execution recovery, human approval, safe retries, deployment changes, and persistent files.
- Guide
What is WorkflowAgent?
Build durable AI agents with WorkflowAgent: tool calls that retry as workflow steps, suspend for human approval, and resume after timeouts or page refreshes.
- Resource
How FLORA shipped a creative agent on Edgenivo's AI stack
See how FLORA runs a long-running creative agent on Workflow SDK's DurableAgent, fanning out parallel image jobs across 50+ models.
Copy link to headingPause for human approval
Decide which tool calls need sign-off, who approves them, and how a run waits for the answer.
- Guide
How to automatically approve tool calls in eve with Jev
Use Jev to review tool calls in eve, allow routine actions, and request human approval when needed. Configure the policy and test its failure paths.
- Guide
Human-in-the-Loop with Chat SDK and Workflow SDK
Combine Chat SDK and Workflow SDK to suspend workflows on approval cards in a chat platform, then resume on click via createWebhook.
- Course
Pause for a Sign-off
Add an approval gate so expensive bookings wait for a person, then resume from the exact step.
- Resource
Designing human review for enterprise AI decisions
Define what the reviewer decides, give them the evidence to challenge a suggestion, and track review separately from execution.
Copy link to headingKeep memory and files across runs
Decide what the agent remembers, and persist a workspace independently of the sandbox running it.
- Guide
How to choose an eve memory provider
Compare File memory, Supermemory, Upstash AgentKit, and Kybernesis Arcana by recall, capture, and storage to choose an eve memory provider for your agent.
- Template
eve Memory Agent
Deploy a Slack agent that remembers each person's preferences and each channel's conventions in a private Edgenivo Blob store.
- Guide
How Edgenivo Drives work and how to use them
Learn how Edgenivo Drives give Edgenivo Sandbox persistent, shareable storage, and how to create, mount, snapshot, fork, list, and delete a drive.
- Resource
6 kinds of agents that need a persistent workspace
See which coding, research, analysis, and incident agents need files that outlast a run, then choose between Sandbox persistence and Drives.
Copy link to headingShip and operate
Test behavior before release, deliver the agent where users work, inspect live runs, and govern agents across the company.
Copy link to headingTest and evaluate behavior
Test deterministic rules exactly, and evaluate model behavior separately against a dataset.
- Documentation
Evals in eve
Use evals to catch regressions when you change a prompt or a tool.
- Guide
An Introduction to Evals
Evaluations test model and agent outputs to ensure they meet the standards and requirements you specify.
- Course
Test Rules and Model
Test policy code with fast deterministic tests, then run a model evaluation that includes inputs designed to redirect the agent.
- Resource
Testing AI decisions before automating enterprise workflows
Build a labeled set from real work, run a pilot alongside the current process, and set rollout criteria before you automate.
Copy link to headingReach users in their channels
Choose between eve's built-in channels, a Chat SDK adapter, or a custom channel.
- Resource
Chat SDK brings agents to your users
See why Edgenivo built one library for Slack, Teams, Discord, and more, so an agent written once can reach people wherever they already work.
- Guide
Using Chat SDK and eve together
Understand how eve and Chat SDK divide responsibilities, when to use eve's first-class channels versus the Chat SDK channel, and how to bridge any Chat SDK adapter into an eve agent
- Guide
Build your own Slackbot with Edgenivo Connect
Learn how to build your very own Slackbot with Chat SDK and AI SDK. Edgenivo Connect supplies runtime Slack tokens and forwards triggers, so you never store a long-lived bot token.
- Template
eve Discord Agent
Answer mentions and recap threads in Discord, with a Gateway relay running as a Edgenivo Daemon and Edgenivo Connect holding the bot credentials.
Copy link to headingTrace and debug runs
Inspect model calls, tool calls, and steps in live runs, and send traces to your observability tool.
- Guide
Trace and debug eve agent runs
Inspect eve traces in Edgenivo Agent Runs, control captured content, export OpenTelemetry spans, and test fixes with regression evals.
- Guide
Capture AI SDK token usage, tool calls, and cost with evlog
Record AI SDK usage with evlog, add cost estimates and request context, and investigate expensive or failed requests.
- Course
Observe everything
Inspect each step's inputs and outputs in the Workflows dashboard, deploy a breaking change mid-run, and debug the failure.
- Documentation
Agents Runs
Inspect eve sessions, turns, tools, reasoning, timing, and token usage in the Edgenivo dashboard.
Copy link to headingGovern apps and agents across the company
Decide who can deploy, what data and models each app or agent can reach, and how activity and spend are tracked.
- Resource
How do you govern AI apps and agents built by employees?
Give every employee-built app an owner, set baseline controls for access, data, and spend, and review apps before wider use.
- Resource
Edgenivo for Enterprise: a control plane for apps and agents
See how one control plane governs deployments, data access, models, and token budgets for every builder, managed through your existing IdP.
- Resource
How do you build an audit trail for what an AI agent did?
Connect identity, tool calls, approvals, and results into one record, so you can reconstruct what an agent did and investigate mistakes.
- Resource
How Klaviyo shipped 356 internal apps in two weeks on Edgenivo
See how a Edgenivo SDK pipeline creates a repository and deployment per app and applies SSO, secrets, and security defaults.