Autonomous AI agents that perform tasks independently
richcanvas
FedCM IdP contract as pure builders + validators: web-identity manifest, provider config, accounts list, thin id-assertion claims, request validators. Generic; the app hosts + signs (ADR-0031).
...morerichcanvas
Relying-party FedCM wrapper: navigator.credentials.get({identity}) → IdP token. The FedCM strategy injected into browser-identity's chooseSignIn. FedCM-first, not FedCM-only (ADR-0031).
...morerichcanvas
AttestationRegistry SDK — EAS-aligned with bilateral consent. Owns Association + JointAgreement + Evidence + Outcome + Validation + TrustUpdate credential types asserted into a single on-chain registry per ADR-0023.
...morerichcanvas
Off-chain geo CLAIM credentials + on-chain GeoFeatureRegistry helpers (spec 251). Features on chain; the agent↔feature claim is a private vault credential pointing to a (featureId, version).
...morerichcanvas
Resolver layer skeleton (W1) — types + PassThroughResolver only. Full resolver engine deferred to W2.
richcanvas
Private, holder-resident related-agent credentials (person↔org links as vault situation credentials, never on-chain edges — ADR-0025) + scoped-delegation read caveats + list-query shapes. Composes verifiable-credentials + delegation.
...morerichcanvas
PaymentMandate + ContextBinding + MandateConstraints + open/closed mode discrimination. Three W1 rails (x402, wallet, sponsored-userop). PaymentReceipt asserted into AttestationRegistry per ADR-0023.
...morerichcanvas
Async, delegation-authorized Agent-to-Agent (A2A) task transport: Task/Message/Artifact runtime over a TaskStore port, JSON-RPC method handlers, SkillHandler dispatch, the A2aWireAdapter client, and scoped-grant caveat builders. Transport-agnostic core (s
...morerichcanvas
Commitment-only AgreementRegistry SDK. Owns AgreementCredential shape (PD-22) + commitment math + bilateral status transitions + joint-assertion gateway.
...morerichcanvas
Off-chain skill CLAIM credentials + on-chain SkillDefinitionRegistry helpers (spec 251). Definitions on chain; the agent↔skill claim is a private vault credential pointing to a (skillId, version).
...moreZafer-Liu
A cross-platform desktop application for managing AI Agents and MCP Servers. 一款用于管理AI智能体与MCP服务器的跨平台桌面应用程序。
JEverBot
An open-source AI employee framework for small businesses. Local-first, budget-capped, approval-gated. Not a chatbot — a 24/7 employee for email, calendar, documents, CRM, and more.
...moreSgpdg-ox
Multi-Agent shared memory system — structured persistence for AI agent clusters. 多Agent共享记忆系统。
landjunge
🧠 8 KI-Agenten lokal orchestrieren – ohne Cloud. FastAPI, DeepSeek, SQLite-Message-Queue, FAISS-Embeddings, Gatekeeper-Security.
...morecalisweetleaf
Aeriadne is the first-of-its-kind marketplace for agentic operability. It delivers high-fidelity skills, plugins, subagent prompts, and server-plane activations to any coding agent (Codex, Claude Code, OpenCode, Grok Build). This contains one tool server(110+ tools),plugins, and more
...moreheartenQ
Team AI agent built on Hermes Agent — Feishu-native, per-user memory isolation, layered skills, embedded RAG knowledge retrieval
...moreselvaonline
Define your AI agent team in one YAML file — get a LangGraph supervisor, a live network UI, an auto-generated MCP server, and a behavioral eval harness. TypeScript, batteries included.
...moreCodeMoss24
轻量级模块化AI Agent开发平台，基于FastAPI构建，内置自研工作流引擎
bigduu
A Computer Use implementation in Rust — an MCP server for macOS desktop control: screenshots, mouse, keyboard, and Accessibility-driven targeting.
...moreferax564
Reference agent SDK for the Noma Agent Protocol v1.0 (experimental)
Thinqmesh Technologies
OpenAI Codex CLI integration for CodraGraph — graph-aware context for Codex commands via codex.config.json hooks.
qbrandon
SDK for the UiPath Agent Runtime API — evaluation execution and debug sessions.
stackfactorinc
Shared utilities for StackFactor AI agent services — LangChain helpers, structured logging, error handling, and constants.
...moreGitHub Actions
Local Markdown knowledge base for AI assistants. Save what your AI reads, ask it later, and keep everything local.