Agent-readable wiki

Eve vs Flue — Agent Harness Comparison

A source-backed comparison of vercel/eve and withastro/flue: two TypeScript frameworks for durable, tool-using agents that share skills, sandboxes, and channels—but diverge sharply in authoring model, runtime layering, deployment posture, and how workflows enter the picture.

Pages

  1. Comparison FrameWhat Eve and Flue each optimize for, the shared problem space (durable agents with tools, skills, sandboxes, and channels), and the criteria—authoring ergonomics, runtime layering, deployment portability, and workflow boundaries—that make cross-repo lessons actionable.
  2. Eve vs Flue Runtime SplitsContrasts Eve's three-way split—channel owns continuationToken, harness does one AI unit, runtime persists and streams—with Flue's harness → session → operation hierarchy and its explicit agents-versus-workflows boundary.
  3. Eve Filesystem Slots & Compiled ArtifactsHow Eve treats the agent/ directory as the contract: path-derived identities for tools, skills, channels, and subagents; defineAgent for additive runtime config; and compilation into inspectable .eve/ runtime artifacts.
  4. Flue createAgent & Agent/Workflow SplitHow Flue authors agents as TypeScript modules with createAgent, defineAgentProfile, and explicit skill/tool imports; how workflows export run(ctx) for finite executions; and how the CLI build graph discovers agents/ and workflows/ layouts.
  5. Durable Execution & CheckpointingCompares Eve's workflow-backed session/turn/step model with automatic step checkpoints and parked work, against Flue's pluggable run and agent-execution stores, dispatch queue, and workflow run IDs exposed over HTTP.
  6. Channels, Ingress & Conversation HandlesEve channels as authored agent/channels/ routes that own continuationToken and auth policy, versus Flue's first-party channel packages (@flue/slack, etc.), blueprints from flue add, and dispatch-based agent admission over a Hono HTTP surface.
  7. Sandboxes, Built-in Tools & SkillsEve's single per-agent sandbox with shipped harness tools (bash, read_file, load_skill, connection_search) and sandbox proxying, contrasted with Flue's adapter-based sandbox factories (local, Cloudflare, blueprint-backed remote) and explicit tool/skill composition in createAgent.
  8. Comparison Verdict & Portable IdeasClosing synthesis: where Eve wins (Vercel-native durability, filesystem discoverability, opinionated harness defaults) versus where Flue wins (multi-target deploy, explicit workflow surface, channel package ecosystem); which patterns—skills, sandbox isolation, session streaming—transfer across either stack.

Complete Markdown

The complete agent-readable Markdown files are published separately from this HTML page.