Autonomous AI agents that perform tasks independently
agentknit contributors
Textual TUI front-end for agentknit coding agents.
AgentBill <[email protected]>
One spend ceiling per agent job, enforced before the call goes out. Bound to a task_ref, not to a calendar month.
Official Python SDK for the Claix document intelligence API (OpenAPI 1.8.2). Typed extraction, document memory, knowledge spaces, and agent-framework tools.
...moreSOKOLAI BV
A maf-sandbox router as a Deep Agents sandbox backend — any backend the router admits (Docker, ACA Sandboxes) behind LangChain's BaseSandbox, with the router's isolation floor and egress policy still enforced.
...moreSeKam68
MCP server plugin for 1C:EDT — 46 tools over the live EDT model: metadata and BSL with unsaved editor changes, forms, DCS, metadata editing, validation, yaxunit run and debug. MCP-сервер внутри 1С:EDT для AI-агентов.
...moreyurika0211
LuckyAgent — 注重长任务规划和系统记忆性的Agent框架
liiiiiiiiil
Build an AI Coding Agent from Scratch, Step by Step | 从零一步步搭建 AI 编程 Agent，边实现边理解 Agent 的工作原理
GunaTeja777
A security-conscious, local-first LLM agent in Go powered by Ollama & Model Context Protocol (MCP). Features defense-in-depth sandboxing, tamper-evident audit logging, and MCP tool orchestration.
...moreZQR1101
具备学情诊断与持续规划能力的自适应伴学智能体（FastAPI + React + RAG，掌握度只认独立有效证据）
henrykbrzoska
Desktop GUI Headless Local-first AI coding agent in Rust (axum, tokio, rmcp, portable-pty) behind HTTP + SSE, with an Angular 20 zoneless client, Tauri 2 desktop shell(and mobile in near future). OpenAI/Anthropic/Z.ai/Ollama + more, MCP bridge, permission engine, PTY terminal.
...moreBlondieredistributed612
Run tool-calling LLM agents locally on Android devices using Termux and llama.cpp with complete data privacy and no external API reliance.
...moreningrenjie
Per-command proxy for DeepSeek Harness: the agent decides which shell commands leave through a proxy, backed by a kernel the plugin installs and supervises itself.
...morerichcanvas
The chain-read authority port: resilient, evidence-bearing, fail-closed reads (isDelegationRevoked, verifySmartAgentSignature, isSessionDelegationAccepted) over multiple injected providers with circuit breakers, divergence detection, and bounded revocatio
...morerichcanvas
Governed collaboration activities (spec 378 huddles): scope, run, participant and lifecycle contracts, admission rules as pure functions, and the media-provider port. No provider SDK, no UI.
...morerichcanvas
The Developer Kit generator (spec 398 §10.3, spec 399 §3.6): `create-app <dir> --template product-repo` writes a product repository — pnpm workspace, exact @agenticprimitives/* pins, agentic.lock.json, `ap doctor` + `ap test` CI, a nightly live-gates work
...morerichcanvas
The Ring-0 agentic orchestration core (ADR-0044): the intent→plan→execute→observe loop, the Planner + ToolInvoker ports, and a deterministic rule-based planner. A first-party app expresses a goal; the loop plans which tools compose to satisfy it and runs
...morerichcanvas
Browser sign-in adapter seam: feature-detect FedCM and choose the browser-native path vs the guaranteed fallback. FedCM-first, not FedCM-only (ADR-0031).
...morerichcanvas
The composed typed resolver (spec 346 §6.3/§8/§9): typed name → subject → derived type → (context → relationship) → permitted publication → bindings, returned as SEPARATE signals (subject / context / relationship / bindings / authority / evidence — never
...morerichcanvas
Agentic Delegated Data Vault seam (spec 277) — the Vault read/write/list interface + data-classification taxonomy + persisted object envelope. Storage/runtime-agnostic; adapters (D1/R2/KMS) layer in behind it.
...morerichcanvas
The two-tier context contract (spec 351 P0.11): public knowledge vs a subject's private records, entity resolution that refuses to guess, and the ContextProvider port.
...morerichcanvas
The authority-aware agent harness (spec 350): the composition root that binds delegation mandates, the tool-policy risk ladder and receipts to the orchestration loop's ports.
...morerichcanvas
Intent engagement protocol core (spec 336 §8): probe → response → offer → acceptance → mandate requirement → execute → receipt as pure documents, JCS digests, and two deterministic reducers. Transport-free; grants nothing.
...morerichcanvas
OpenAI-compatible chat-completions binding for the @agenticprimitives/orchestration Planner / AnswerComposer ports (the in-repo adapter, chain-state-viem pattern). Vendor-neutral: the consumer supplies baseUrl + model (Groq, Ollama, OpenRouter, …). create
...moreGitHub Actions
Apply and verify SkillRights declarations on AI agent skills: execution permitted, training rights reserved, in one line. No accounts, no telemetry, no network.
...more