Search

Versioned scientific modeling engine and Agent Skill with Model IR, simulation, fitting, uncertainty, causal/Bayesian inference, formal/numerical validation, reproducible export, REST, MCP and CLI.

Let an AI agent pay, and prove what it could not. A tamper-evident record of every payment attempt, including the refusals, for agent-operated wallets. Built for Canton Network; works anywhere. Zero dependencies.

LangChain tools for DNS Doctor: scan, diagnose and fix a domain's SPF, DMARC and DKIM, check global DNS propagation, audit SPF includes. Deterministic verdicts and copy-paste records from dnsdoctor.dev, never a guessed record.

AgentShip observability — the OpenTelemetry implementation of the Observer port: span-tree exporter pipeline (Phoenix/Langfuse/LangSmith), the one-per-process LiteLLM cost/token callback, and the studio launcher. The vendor-free contract lives in agentship-core.

AgentShip LangGraph engine — the default real-model runtime, with a LiteLLM model source that routes one `model:` string to any provider.

Find Claude Code skills that fail silently - never loaded, never chosen, or shadowed by another skill.

Kanban board for managing AI agent sessions

octet — a native coding agent for the terminal, with provider integrations and extensible tools.

纯 Kotlin 原生 Android AI 智能体：多模型接入、子智能体协作、在线插件市场、技能自动引用、root/Ubuntu 终端、长期记忆

Human-controlled Playwright testing workflow toolkit

eve extension that gives durable AI agents BlitzReels video editing, clipping, generation, and export tools.

Code-quality feedback for LLM coding agents (CLI via cargo install kiss-ai).

Lineage-gated shared memory for multi-agent analytics: block cross-department data leakage and catch silent metric-definition conflicts.

Signed, offline-verifiable receipts for every tool call in anthropics/commerce-agents, on all three of its runtimes.

Deterministic onboarding and maintenance for hardened coding-agent containers

TUI agent that drives your Edge browser via CDP to auto-produce WeChat article layouts on xiumi.us (command: xiumi)

Minimal multi-provider agent library with tools

MindAgent 是一个基于 Python 和 `asyncio` 的 Agent Runtime。它使用状态机约束生命周期，通过 ReAct 循环驱动模型决策，并将 Provider、Tool 和上下文管理分离。

A plan-approved, tier-routed agent loop over LoadCoach, in which every step is proposed, approved against governance policy and remaining budget before it executes, and fully reconstructable afterwards.

Your agent remembers this repo, and it will not lie about it. Local-first memory for Claude Code and friends, with receipts.