中文
~/home / Show HN
Show HN

Makoto – Block AI agents when their claims contradict their logs

Makoto – Block AI agents when their claims contradict their logs is a skill AI agent for Identify and resolve inconsistencies between an AI agent’s statements and its logged behavior to enhance trust and consistency. Pricing: not stated on the product page. As of 2026-09-12, KanonAgent records 1 upvotes. First indexed by KanonAgent on 2026-07-08.
An AI agent that detects and corrects contradictions between its own claims and actions to improve reliability.
Makoto – Block AI agents when their claims contradict their logs — official preview image
1 upvotes
Tracked by Kanon since Jul 8, 2026
no signal yet
status
20/100
momentum · conf 0.65
20d
tracked since 2026-08-22
6
evidence records

No signal event on file yet — status is unknown, not "quiet".

📈 Timelinewhat changed, and when
🔎 Known / Unknown 12 of 23 fields unknown
Machine-callable— unknown —
Open source1 inferred 1 quote(s)
Self-hostable1 inferred 1 quote(s)
Bring your own key— unknown —
Autonomy level2 inferred 2 quote(s)
Pricing model— unknown —
Integrationsclaude inferred 1 quote(s)

“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.

🤖 Agent teardown · skill
Job to be doneIdentify and resolve inconsistencies between an AI agent’s statements and its logged behavior to enhance trust and consistency.
AutonomyL2 · tool-calling(evidence: "watches the agent's _own_ tool calls and blocks the ones…")
Who it is forAI system users
Prerequisitesopen source · self-hostable
Integrationsclaude
Traction · why it is risingOne vote indicates early interest in addressing AI self-contradiction, a key issue for trust and compliance.
Why it matters

Tackles the problem of AI 'talking out of both sides of its mouth,' making it a foundational step toward trustworthy AI.

Evidence quotesverbatim, from the product’s own materials

“public GitHub repository (README fetched)”— structural
“An integrity hook for Claude Code”— readme
“watches the agent's _own_ tool calls and blocks the ones”— readme
“blocks the tool call (or the end-of-turn) and hands the agent a one-line correction to retry”— readme
“integrity hook for Claude Code that watches the agent's”— readme
“An integrity hook for Claude Code that watches the agent's own tool calls”— readme
Signal source: Show HN
Visit official site →
📛 Official badgefor your site / README
Makoto – Block AI agents when their claims contradict their logs badge
Building Makoto? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
Share on X
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.

FAQ

What is Makoto?

An AI agent that detects and corrects contradictions between its own claims and actions to improve reliability.

What does Makoto do?

Identify and resolve inconsistencies between an AI agent’s statements and its logged behavior to enhance trust and consistency.

Why does Makoto matter?

Tackles the problem of AI 'talking out of both sides of its mouth,' making it a foundational step toward trustworthy AI.

Is Makoto open source?

Yes — Makoto is open source.

Can I self-host Makoto?

Yes — Makoto can be self-hosted.

What does Makoto integrate with?

claude

How popular is Makoto?

As tracked by KanonAgent: 1 upvotes (first indexed 2026-07-08).

What are the best Makoto alternatives?

Similar AI agents tracked by KanonAgent: open-design, deer-flow, Agent-Reach, ruflo, career-ops, orca.

Makoto – Block AI agents when their claims contradict their logs alternatives — similar AI agents

open-designdeer-flowAgent-Reachruflocareer-opsorca

Where this fits — browse the same shelf

AI Agent Skills & PluginsAI agents for Multi agent orchestrationAre there open-source AI agents for Multi agent orchestration?Can I self-host an AI agent for Multi agent orchestration?AI agents that work with ClaudeSelf-hosted & open-source AI agents