AgentML

Prompting is guessing. AgentML is declaring. A new language for agents who actually follow the rules. Created and maintained by @AgentflareAI

[AgentML @AgentMLdev]

Flat tool lists are dead. Stateful tools are next.

AgentMLX doesn’t hand an LLM a flat list of APIs — it gives it a state-scoped toolset that evolves with the agent’s behavior.

[Gabe @glwillen]

Built a graph database extension for SQLite with full Cypher query support. Complete execution pipeline in C99.
Posted on HN: https://t.co/d7d9QqUrCx

@sqlitenews @_sqlite_ @kellabyte @andy_pavlo @simonw @neo4j

[AgentML @AgentMLdev]

Memory belongs inside the agent

In AgentML, memory is a first class citizen that lives directly in the runtime.

We’re combining https://t.co/APVmzHg9I6 our open sourced openCypher compliant SQLite graph extension, with sqlite-vec to give every agent local and secure memory built in.

From key value to vector search to full graph traversal, memory in AgentML is native, composable, and runs anywhere SQLite runs.

[AgentML @AgentMLdev]

What applications do you see for agent generated agents? I'd love to hear your thoughts.

[AgentML @AgentMLdev]

Building AI agents shouldn't require wrestling with UI builders or writing everything from scratch, and I suspect many of you feel the same.

This weekend, I built the first proof of concept AgentML agent designed to create other AgentML agents.

[AgentML @AgentMLdev]

Communication is builtin

[AgentML @AgentMLdev]

@JafarNajafov Context overload does lead to performance degradation over time. Sub-agents and just-in-time retrieval help, and AgentML adds schema validation for state transitions to keep flows deterministic without accumulating noise. https://t.co/viacjuLiYT

[AgentML @AgentMLdev]

@ericzakariasson Tracking transitions step-by-step is essential to catch those failures early. AgentML uses deterministic state machines for replayable logic and built-in compliance checks, which helps turn agent prototypes into reliable systems. https://t.co/viacjuLQOr

[AgentML @AgentMLdev]

@kiran__a__n @QodoAI Guardian Agent's stability trends are 🔥 https://t.co/viacjuLQOr amps it with AML for root-cause tracing in agent logic (no more black-box fails).

What's your toughest reliability bug? #QodoAgentChallenge
@kiran__a__n

[AgentML @AgentMLdev]

@ChiefScientist Signing the Reliable AI Manifesto! AgentML embodies this with XML-like AML for traceable, policy-enforced agents. E.g., enforce 'no hallucination' via explicit states. Thoughts on integrating deterministic langs into your pillars? Repo: https://t.co/kHUiI0eq3Z @ChiefScientist

[AgentML @AgentMLdev]

Flat tool lists are dead. Stateful tools are next.

AgentMLX doesn’t hand an LLM a flat list of APIs — it gives it a state-scoped toolset that evolves with the agent’s behavior.

[AgentML @AgentMLdev]

Nearing the completion of our @langchain langgraph transformer.

Watch us build in public as we rapidly work towards a one definition, infinite agent framework paradigm.

[AgentML @AgentMLdev]

https://t.co/kHUiI0eq3Z

[AgentML @AgentMLdev]

We are opening up AgentML a Deterministic Language for Agent Behavior. AgentML combines the usability of XML with the predictability of state machines, giving you complete control over agent behavior. MIT License.

Link in comments.

[AgentML @AgentMLdev]

We go live this week.