chetan conikee

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by @modiqoai to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install → modiqo.ai

GitHub repo: github.com/modiqo/waggle

@conikeec cool will check it out :)

@yoheinakajima BTW: @debasishg and I were reviewing ActiveGraph DAG construction from our own perspective modiqo.ai/docs .. The articulation and reasoning is excellent. We might publish our paper soon and might land up citing it for sure as we lots of similarities in approach

"The paper's insight connects to a broader pattern: AI agents are essentially distributed systems with unreliable components (the LLM), and we should apply distributed systems patterns to them." developersdigest.tech/blog/log-is-th…

cc @bigdata

@yoheinakajima Additionally , we also opensourced skillspec.sh/research.html that provides a state machine like semantic to processing prose based skills (which otherwise do not provide any guarantees with plain inference) github.com/modiqo/skillsp…

@yoheinakajima Hey @yoheinakajima : We completely agree with this assertion and open sourced waggle (waggle.sh) that solves one small aspect of it paper: waggle.sh/paper.pdf code: github.com/modiqo/waggle x.com/conikeec/statu…

The Hidden Cost of Giving AI Agents Shell Access 🎯 CLIARE is a 🆕 open source tool for measuring how ready a CLI is for AI agents. It evaluates discoverability, error handling, machine readable output, and other practical capabilities → gradientflow.com/i-changed-my-m…

🆕Measuring AI Readiness for Command Line Tools 🎗️CLIARE is an open-source tool that probes the real installed binary, not your docs, and scores it across 6 dimensions: discoverability, valid invocation, completion without hanging, error messages & more → gradientflow.substack.com/p/i-changed-my…

🆕 Measuring AI Readiness for Command Line Tools 🎗️ CLIARE is an open-source tool that measures how agent-friendly a CLI actually is. It probes the real installed binary, not your docs, and scores it across six dimensions: discoverability, valid invocation, completion without hanging, clear error messages, machine-readable output, and read-only safety. → gradientflow.substack.com/p/i-changed-my…

通过黑盒运行时探测为 CLI 生成证据驱动的命令索引、就绪评分和安全审查报告，让 AI agent 不需要反复试错就能可靠使用终端命令。 github.com/modiqo/cliare 一个 Rust 写的 CLI 审计工具，通过黑盒运行时探测来评估命令行界面是否适合 AI agent 使用。它把 CLI 当作黑盒来测，记录运行过程中的真实行为，推断命令结构，发现副作用，然后生成命令索引、问题清单、评分卡和角色报告。

Open sourcing Cliare cliare.sh/why-cliare.html

Excited to open source cliare.sh/why-cliare.html

@yoheinakajima @FlyMy_AI We have been doing this for quite and we are ex-commiters/authors on scala, Erlang, rust modiqo.ai

this is a great approach, seeing this more @flymy_ai also does this when you build an agent via their api, they'll build a deterministic reusable workflow, except for where you need models

@josephruscio at @heavybit had discussed this topic at great length here heavybit.com/library/articl… cc @AndrewPark1313

This is a really interesting approach to operationalizing #agentic #skills. Try the repo here: github.com/modiqo/skillsp…

Part 1 in my series on Low Level System Design in Rust is live now - This part covers: • how to lay out a shared Rust struct by who-touches-what • zoning fields by write owner and frequency, then • padding the cross-core ones to avoid false sharing and prefetcher-induced contention Cache-Conscious Data Layout in Rust: Field Zoning, False Sharing, and the 128-Byte Rule - debasishg.github.io/blog/part1-cac…