AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Multi-Agent/
council-of-high-intelligence
council-of-high-intelligence logo

council-of-high-intelligence

Active·★ 4.9k·MIT·Updated 2026-11-16

Council of High Intelligence (CHI) by 0xNyk is an open-source multi-perspective deliberation harness (MIT license) engineered for Claude Code, Codex, Gemini CLI, and OpenCode. It is explicitly designed for high-stakes, irreversible architectural, commercial, or security decisions that cannot be safely entrusted to a single linear LLM completion.

Instead of producing an agreeable consensus, the council assigns a complex problem statement to deliberately divergent analytical personas (e.g. pragmatist builder, adversarial contrarian, security auditor, systems architect). It enforces independent opening positions, mandates an adversarial cross-examination round where personas must attack each other's assumptions, and compiles a structured verdict that preserves unresolved questions, minority dissents, explicit kill criteria, and immediate concrete actions.

The harness supports flexible operating modes: Full Council for maximum adversarial depth, Quick Triad for rapid three-lens reviews, and Duo Dialectic for polar trade-offs. While invaluable for breaking cognitive bias in engineering leadership, convening a full council consumes significant tokens and execution time, making it ill-suited for trivial syntax lookups or reversible micro-decisions.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-12.

License
MIT
Latest release
v1.2.0 · 2026-07-04
Last commit
2026-11-09
Contributors
11
Forks
456
Open issues and PRs
23
First published
2026-03-02

Source: GitHub, npm and PyPI public APIs.

#agent-skill#ai-agents#claude-code#codex#decision-making#deliberation#dev-tooling#gemini-cli
↗ Visit site★ GitHub
01

Features

01Independent initial analysis precedes cross-examination.
02Modes include full councils, quick panels and duo debates.
03Verdicts retain uncertainty, kill criteria and a next action.
02

Why choose it

+Forces authentic cognitive diversity through adversarial persona cross-examination, eliminating single-model blind spots.
+Structured decision artifacts preserve minority dissent, explicit failure/kill criteria, and concrete next actions.
+Seamless client integrations across Claude Code (/council plugin), Codex, Gemini CLI, and OpenCode.
+Flexible operational tiers including Full Council, 3-persona Quick Triads, and 2-member Duo Dialectics.
03

Trade-offs

!Deliberation rounds require substantial context token consumption and noticeable multi-turn latency.
!Unsuitable for simple, factual, or highly reversible coding decisions where speed is paramount.
!Output reasoning quality is strictly bounded by the underlying model's capacity for nuanced analytical roleplay.
!Provides decision synthesis and risk auditing only; does not automatically execute the chosen architectural change.
04

Maintenance check

ActiveChecked: 2026-11-12
Last commit
2026-11-09
Commits, last 90 days
23
Releases, last 90 days
0
Latest release
v1.2.0 (2026-07-04)
Open issues
23
Recent issues with at least one comment
6/15
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #88 bug: --no-auto-route is not default2 comments · 2026-11-06
  • #34 proposal: add support for modular python agent frameworks (Agno, LangGraph, etc.)2 comments · 2026-05-26
  • #71 feat: add Abraham Wald as 19th council persona (survivorship bias and selection-corrected inference)1 comments · 2026-08-01
  • #28 tracking: 2026 MAD literature enhancement candidates (E1–E8)1 comments · 2026-05-18
  • #84 codex_exec seats fail outside a git repo and can hang waiting on stdin0 comments · 2026-09-24

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

claude-code
Plugin installation documented
Verified via docs
codex
Dedicated installer flag
Verified via docs
gemini-cli
Dedicated installer flag
Verified via docs
opencode
Dedicated installer flag
Verified via docs
06

Use cases

↳Compare competing architecture choices.
↳Examine a product or strategy decision.
↳Record predictions and evidence for a later checkpoint.
07

Alternatives

⚡Top VS:
VSmunder-difflin★9.6k→VStaste-skill★117.7k→VSagentes-chat★1.7k→VSagmsg★1.6k→
orca logo
orca★ 127.8k
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
munder-difflin logo
munder-difflin★ 9.6k
an open-source alternative to the dots, bots and muses of the world, run an office of claude code/codex like agents on your laptop, sandboxes or anywhere, uses your existing subscriptions
VSCompare→
taste-skill logo
taste-skill★ 117.7k
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
VSCompare→
agentes-chat logo
agentes-chat★ 1.7k
Open-source, self-hosted Slack alternative where your team and AI agents work together in channels and DMs. Agents run on Claude, ChatGPT/Codex, Gemini or Grok, with MCP tools, their own computer and browser, routines, memory and approvals. Web, desktop and phone apps. Docker Compose + Postgres. AGPL-3.0.
VSCompare→
agmsg logo
agmsg★ 1.6k
Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.
VSCompare→
cezar logo
cezar★ 1.1k
Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI coding agents in parallel — locally or 24/7 on your own server.
VSCompare→
nuwa-skill logo
nuwa-skill★ 38.5k
你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
VSCompare→
video-shotcraft logo
video-shotcraft★ 21.0k
AI video skill for Claude Code & Codex — cinematic, editable product promos with Remotion: 124 shot recipe cards, 150 motion previews, beat sync, sound design, Motion Workbench & JianYing (CapCut CN) export.
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Use cases07Alternatives
0xNyk /
council-of-high-intelligence
↗

Structured multi-perspective deliberation engine for complex decisions across Claude Code, Codex, and Gemini CLI

4.9k456MIT
Last commit2d ago
StatusActive
CategoryMulti-Agent
Contributors11
Latest releasev1.2.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.