evo vs fractal
Karpathy-style autoresearch on any codebase: /evo:discover instruments the benchmark, /evo:optimize runs tree search with parallel subagents in worktrees. Plugin for Claude Code, Codex & co. — versus — Hierarchical agent loops: nodes iterate toward a goal in their own git worktree and spawn children for subtasks — the tree grows to fit the problem. Hard caps, SQLite run log, live TUI.
Both grow trees of worktree-isolated agent loops. evo's tree searches for a better SCORE on a fixed benchmark; fractal's tree decomposes a TASK into subtasks. Optimization vs delegation — same shape, different objective.
| evo | fractal | |
|---|---|---|
| Stars | 1.4k | 614 |
| Forks | 101 | 44 |
| Language | Python | Python |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | 10 days ago | today |
| Topics | coding, skills | coding, orchestration |
| Curated connections | 4 | 3 |
evo — the curator's take
Where the autoresearch skill is a greedy hill-climb on one branch, evo is the industrialized version: tree search over committed nodes, parallel subagents in isolated git worktrees sharing failure traces, regression gates that discard bad experiments, frontier strategies (argmax to GEPA-inspired pareto), and a dashboard. Benchmark discovery is the sleeper feature — it figures out what to measure before optimizing. Runs on 8 agent hosts, local or remote sandboxes (Modal, E2B, Daytona, AWS). NOT for codebases without a mechanical metric — no benchmark, no loop — and unattended parallel agents editing your repo demand real gates; the hosted 'evo platform' beta hints where the business model lands.
fractal — the curator's take
The self-organizing answer to multi-agent coding: no fixed pipeline — a node that finds a separable subtask spawns a child for it, bounded by hard caps on depth, children, iterations, cost and time, with an operator able to steer or kill any loop from the TUI. The README's warning deserves framing: every seeded config DISABLES the agent's approval gate (bypassPermissions, danger-full-access, --yolo) because unattended loops can't stop to ask — and worktrees isolate the branch, NOT the filesystem or network. Treat that as a hard requirement to run it inside real isolation, not a footnote. NOT for work needing deterministic process: if you want the same stages every run, you want a workflow graph, not a fractal. 614 stars — early.