Aegis

Stop babysitting your agent. Aegis makes your agent plan against your real baseline before it edits, prove completion with fresh evidence, and leave simple tasks alone — you get fewer reworks, safer changes, and less blind trust in "done".

What You Get

Aegis is a method pack that makes AI coding agents work like disciplined engineers — so you don't have to watch them.

• Fewer reworks. Your agent aligns with your project's real baseline — owners, contracts, boundaries — before touching code. It stops guessing, and so do you.
• Safer changes. Measured on a frozen held-out A/B benchmark: contract pass rate 61.67% → 93.33%, unsafe outcomes 13.33% → 0%.
• Proof before "done". Completion claims ship with fresh verification evidence, covered scope, and residual risk. You read evidence, not vibes.
• No ghost code. Retired fallbacks and old paths are tracked or removed with a retirement trigger — technical debt stops accumulating silently.
• Simple tasks stay simple. Trivial requests stay on the fast path; ceremony only appears when the task genuinely needs it.
• UI/UX rules on demand. UI/UX governance carries project design rules, lower user effort, and scoped experience evidence through design, implementation, review, and verification.
• One method pack, every host. The same discipline works across Codex, Claude Code, OpenCode, Kimi, and other skill-aware hosts.

These numbers are bounded advisory evidence from Aegis 2.7.6 (2026-08-11), not a measurement of this release, a universal-quality claim, or completion authority. See the full benchmark and its limitations.

Quick Install

New here? The fastest start is one prompt to your agent — the full install-and-verify flow is below.

Give this prompt to your AI coding agent:

Read https://github.com/GanyuanRan/Aegis, identify my current AI coding host, and install Aegis globally using the correct host guide. If the host is the official DeepSeek Harness (`dsh`), treat global/minimal installation as native profile-plugin installation with `dsh plugin --profile <profile> add "git+https://github.com/GanyuanRan/Aegis.git"`; do not silently substitute the direct-child compatibility path unless the plugin manager is unavailable and I explicitly approve compatibility mode. Restart or reload the host if needed, then run complete-install verification from the installed Aegis method-pack root. Do not run the doctor command from the target project directory. First locate `<aegis-method-pack-root>`, then run `cd <aegis-method-pack-root> && python scripts/aegis-doctor.py --write-config --json`. Treat the install as complete only if the JSON includes `"ok": true`, `"workspaceSupport": "available"`, and `"configStatus": "configured"`; if the host uses a separate skill discovery directory, also verify it with `--discovery-root <path>`; if the host guide declares a skill directory name prefix, also pass `--discovery-name-prefix <prefix>`. Also complete the selected host guide's native activation and automatic-entry checks; file discovery or a generic doctor result alone is not sufficient when the host provides a plugin, hook, or session-start bootstrap contract.

DeepSeek Harness also supports the official npm package @ganyuan_ran/aegis. Choose one channel per profile; see the DSH installation, update and migration guide. The prompt above selects Git; npm installations use the scoped package name.

Measured Agentic Benchmark

A frozen held-out A/B benchmark for Aegis 2.7.6 (2026-08-11) kept the Codex client, prompts, projects, tool policy, and requested the same gpt-5.6-sol / xhigh setting in both arms; only the Aegis projection differed. Across 120 valid runs on 20 cases, contract pass rate was 61.67% → 93.33% (+31.67 pp) and unsafe outcomes were 13.33% → 0%. The 95% case-cluster interval was +15.00 pp to +50.00 pp. This is bounded advisory evidence; review was arm-hidden technical review, not independent human review, and host events did not return the observed model identity.

Sanitized JSON · English table · 中文表格 · Methodology

A newer matrix-v7 standard snapshot for Aegis 2.10.8 covers 22 cases with one observation per arm and case. It uses a different run profile from the extended snapshot above and does not measure the changes in this release.

Try Aegis Methods in a Coding Runtime

Autoloom is our AI coding desktop client. It brings Aegis's change necessity analysis, complexity governance, and delivery review into development execution, helping you spend less time repeating instructions and inspect the evidence behind delivered changes.

Currently available as a Windows x64 Alpha. The client is free; choose your model provider, which bills model usage separately.

Explore Autoloom · Download Alpha

This is the beginning of the README. Read the rest at the original. Read the full README ↗