Evot

An agent engine that completes complex, long-running work with minimal tokens and maximum quality.

Every gain measured under a rigorous trace + eval framework — earned through relentless iteration, never guessed at.

News · Benchmark · Why · Dashboard · Install · Quickstart · Dev

• 2026-06-16 [REPL] Shift+Tab cycles reasoning effort; persisted per session.
• 2026-06-05 [Dashboard] Built-in web dashboard — server metrics, sessions, usage, and tool traces.
• 2026-05-30 [Engine] Major refactor — four-pass compaction, pi-aligned parallel tools, leaner core.
• 2026-05-11 [Skills] Built-in opencli — browser control, logged-in cookies, Feishu/Lark, Twitter/X.

Same task, same eval environment, different models. evot completes the work with fewer tokens, less time, and lower cost — on both frontier and open-source models.

Claude Opus 4.6	DeepSeek V4 Pro

Task: Fix a real bug in serde_json (issue #979) — investigate root cause, apply fix, write regression test, verify all tests pass.

All agents produce correct, passing code. The difference is how they manage context.

Give the LLM less context, but higher-quality context. Where other agents call the LLM to summarize when context overflows — burning extra tokens and time — evot uses zero LLM calls for context management:

• Algorithmic compaction — a four-pass Rust pipeline (Reclaim → Shrink → Collapse → Evict) runs in microseconds between turns. Images downgrade to path references; old turns collapse to one-line summaries.
• Spill to disk — large tool results write to disk with a short preview. The model re-reads on demand instead of carrying megabytes in context.
• Compaction markers — structured metadata (files modified, conclusions, environment state) survives compaction, so progress is never lost.

Every gain is earned under a rigorous trace + eval framework, not guessed at. Each engine change is measured against live traces and a reproducible benchmark pipeline — the same real-world tasks run against Claude Code and Codex (latest versions) — before it ships. Token usage, cost, time, and success rate must improve or hold. Relentless trial and iteration, where the numbers decide what stays. Continuous improvement, no regression.

Evot ships with a built-in web dashboard for real-time observability: server resource usage, all connected sessions, and per-session detail — token usage, tool call sequences, and span-level traces.

Overview — server metrics & sessions	Session detail — usage & tool traces

curl -fsSL https://evot.ai/install | sh

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

1. Set your API key

Create ~/.evotai/evot.env:

# Anthropic (default)
EVOT_LLM_ANTHROPIC_API_KEY=sk-ant-...
EVOT_LLM_ANTHROPIC_BASE_URL=your-anthropic-base-url
EVOT_LLM_ANTHROPIC_MODEL=claude-opus-4-6
# Multiple models: EVOT_LLM_ANTHROPIC_MODEL=claude-sonnet-4-6,claude-opus-4-6

# Or OpenAI
# EVOT_LLM_OPENAI_API_KEY=sk-...
# EVOT_LLM_OPENAI_BASE_URL=your-openai-base-url/v1
# EVOT_LLM_OPENAI_MODEL=gpt-5.5

# Or DeepSeek (Anthropic-compatible)
# EVOT_LLM_DEEPSEEK_API_KEY=sk-...
# EVOT_LLM_DEEPSEEK_BASE_URL=https://api.deepseek.com/anthropic
# EVOT_LLM_DEEPSEEK_PROTOCOL=anthropic
# EVOT_LLM_DEEPSEEK_MODEL=deepseek-v4-pro

# Or Xiaomi MiMo-V2.5-Pro (Anthropic-compatible)
# EVOT_LLM_XIAOMI_API_KEY=tp-...
# EVOT_LLM_XIAOMI_BASE_URL=https://token-plan-cn.xiaomimimo.com/anthropic
# EVOT_LLM_XIAOMI_PROTOCOL=anthropic
# EVOT_LLM_XIAOMI_MODEL=mimo-v2.5-pro

Use --model provider:model for one-off overrides.

2. Run

evot                                          # interactive REPL
evot -p "summarize today's PRs"               # one-shot task
evot -p "review this" -f ./src/main.rs        # attach file context
evot -p "continue work" -c                    # continue latest session in cwd
evot -p "continue work" -r my-session         # resume or create session

In the REPL: /help lists commands, Shift+Tab cycles the reasoning effort.

make setup        # install Rust toolchain, git hooks
make test         # all tests (engine + CLI)
make install      # compile standalone binary to ~/.evotai/bin/evot

Apache-2.0