Search

ACGS rule-based tool-call governance for CrewAI, as native tool call hooks

Placeholder package

Give any AI agent a public A2A (Agent2Agent) endpoint: a Cloudflare Worker, a wake webhook, or scheduled checks

ACGS rule-based tool-call governance for Pydantic AI agents, as a capability

Self-hosted runtime for Levain agents: run an agent's nodes on your own machine or container while the platform drives the recipe

Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...

Temporary package placeholder for staged publishing

Eval harness for Claude Code agents: golden tasks, rule checks, LLM-judge rubrics, traces, cost/latency, regression gate.

ACGS rule-based tool-call governance for OpenAI Agents SDK function tools, via tool guardrails and approvals

A web-reading tool for LLM agents that returns the parts of a page relevant to a question, verbatim

Read and use Noir agent policies (device registry, agent registry, payment escrow) on Stellar from any app.

Create a Fleet agent project: npm create @apralabs/agent-kit my-agent

Hierarchy-aware, time-aware memory for LLM agents and RAG on hyperbolic (Poincaré ball) geometry. Official reference implementation of the memory component of 'LLM Orchestration with Geometry-Aware Memory' (IEEE ICBDML 2026).

Scenario-first reference implementation of 'LLM Orchestration with Geometry-Aware Memory' (IEEE ICBDML 2026): metacognitive controller, provider-agnostic ensemble with throttling detection, multi-objective synthesis, on top of poincare-memory.

A plug-in backup layer for coding agents: preserves state before every tool call modifies it

Pre-open repo agent-surface audit: per-harness OPEN / OPEN-QUARANTINED / DO-NOT-OPEN verdict on a received repo's complete agent-control surface, before your agent's first git call.

Claude Code skills and a nine-agent pipeline for first-pass contract and lease review. Not legal advice.

Lint Claude Code SKILL.md and subagent files: frontmatter, description triggers, token size, broken file references, and overlapping descriptions that make the wrong skill fire.

SDD agnóstico: especificações como contrato, verificação fora do LLM.

A local-first AI coding agent with one gateway for five LLM providers and a self-provisioning database.