GitHub - evotai/evot: Evot - A self-evolving agent engine for long-running, high-complexity work.

3 min read Original article ↗

Evot

Evot

A self-evolving agent engine — fully observable, token-efficient, built for long-running complex work.

Everything Claude Code / Codex can do — half the tokens, fully observable, in 20k+ lines of Rust.

The engine behind evot.ai

News · Why · Install · Quickstart · Dev · Community

📢 News

  • 2026-04-13 🏷️ Project renamed from BendClaw to Evot.
  • 2026-04-13 🔌 [Skills] Auto-load Claude Code skills.
  • 2026-04-11 🧠 [Memory] Auto-load Claude Code memories for the current project.
  • 2026-04-10 🎯 [Plan Mode] Add ask_user tool for interactive option selection.
  • 2026-04-10 🌐 [Web Fetch] SPA support via headless Chrome fallback.

⚡ Why Evot

Claude Code and Codex dump everything into context — bloated outputs, stale history, noise. Tokens wasted. Quality drops. No visibility into why.

Evot doesn't waste a single token — and proves it.

  • Clean context, always. Every prompt to the LLM is minimal, high-signal, zero-waste.
  • Blazing fast. Fewer wasted tokens → fewer turns → complex tasks done in half the time.
  • Fully observable. Every LLM call, tool execution, and compaction tracked end-to-end. This data feeds back into the engine — Evot evolves its strategy so the next prompt is always leaner than the last.

Not a CLI wrapper. The agent engine you build on — ships with interactive REPL, CLI, and server.

Built on a Rust engine with a TypeScript CLI powered by Ink.

Evot in action

Installation

One-liner (recommended)

From source

git clone https://github.com/evotai/evot.git
cd evot
make setup && make install
evot

Quickstart

Create ~/.evotai/evot.env:

# Provider: "anthropic" or "openai"
EVOT_LLM_PROVIDER=anthropic

# Anthropic
EVOT_ANTHROPIC_API_KEY=sk-ant-...
EVOT_ANTHROPIC_BASE_URL=https://your-api-endpoint.com
EVOT_ANTHROPIC_MODEL=claude-opus-4-6

# OpenAI
EVOT_OPENAI_API_KEY=sk-...
EVOT_OPENAI_BASE_URL=https://your-api-endpoint.com/api/v1
EVOT_OPENAI_MODEL=gpt-5.4

Only the active provider's keys are required. Set EVOT_LLM_PROVIDER to switch.

evot                              # interactive REPL
evot -p "summarize today's PRs"   # one-shot task
CLI flags & options
Flag Description
-p, --prompt Run a single prompt and exit
--resume <id> Resume an existing session
--model <model> Override the configured model
--output-format text|stream-json Output format (default: text)
--max-turns <n> Limit agent turns (default: 512)
--max-tokens <n> Limit total tokens
--max-duration <secs> Session timeout in seconds (default: 3600)
--append-system-prompt "..." Inject extra system instructions
--verbose Enable info-level logging

Development

make setup        # install Rust toolchain, git hooks
make check        # fmt + clippy
make test         # all tests (engine + CLI)
make test-engine  # Rust engine tests only
make test-cli     # CLI tests only (TypeScript)
make dev          # build NAPI + run CLI in dev mode
make install      # compile standalone binary to ~/.evotai/bin/evot

Community

License

Apache-2.0

Built with 🦀 + TypeScript by Evot AI