#ai-agents

Agent Receipts — cryptographically signed audit trails for AI agent actions. Protocol spec, SDKs (Go, TypeScript, Python), and MCP proxy.

AI integration layer for Jido agents with LLM orchestration and reasoning strategies.

KDNA CLI for validating, planning, loading, managing, and consuming judgment assets.

Standalone MCP server that gives AI agents access to your Obsidian vault — hybrid search, memory, tasks, files, OAuth 2.1. Run locally, self-host, or one-click deploy for remote access.

Harn is a programming language and runtime for building AI agents.

Local-first control surface for AI coding agents, workspaces, worktrees, terminals, diffs, previews, and paired-device access.

🔐 The password manager for terminal users and AI agents. Age-encrypted, keyring-cached, MCP-ready. Zero telemetry.

Skill-first control plane for creative tools: shared MCP/REST runtime, gateway, CLI, marketplace, safety, and observability across studio pipelines.

Your brand, every component, out of the box. The Devalok Design System: accessible React and Tailwind 4 CSS-first components, OKLCH design tokens, and AI-agent-ready docs.

The system of record for AI-written software. A persistent graph of entities, relationships, changes, and provenance, so humans and AI agents see what a change touches before it merges. Beside Git today.

Your local-first AI ad ops crew. Works with Claude Code, Cursor, Codex & Gemini.

Telegram for AI agents -- messages, chats, media, and contacts across both bot and full user-account modes.

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.

Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman collections, OpenAPI specs, and environments via Model Context Protocol (MCP)

Official Node.js, Python, and Go SDKs plus the primitive CLI for Primitive — email infrastructure for AI agents. Generated from the OpenAPI spec.

AI Agent Evaluator & Red Team Platform

Local-first Memory Framework for AI Agents · 99.2% LongMemEval-S retrieval @ k=10 · Supports Claude · Antigravity · LangChain · Hermes · Gemini · OpenCode · OpenClaw · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable

Pilot Protocol: The Internet of Agents

PWN is an open security automation framework that aims to stand on the shoulders of security giants, promoting trust and innovation.

The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)

The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.

Multi-resource rate limiting for LLM APIs. Reserve tokens before you call, refund what you don't use, stay under the limit across workers.

Spec-driven development framework — AI agents that think before they type

The most autonomous agent framework. No approval loops. No babysitting. Configure once, forget forever.

Your AI agent develops firmware on its own: build, flash, stimulate real hardware, observe, fix - policy-gated MCP tools + pytest plugin.

CLI for managing AI agent squads. Status, memory, goals, feedback, and dashboard for your autonomous agents.

TypeScript/Node.js SDK for adding Agent Assembly governance to agent apps and tool calls.

Unofficial FastMCP extensions, created by Airbyte for the FastMCP and Airbyte community. Used by our own MCP servers and inspired by our usage patterns and emerging best practices.

AnchorBrowser-SDK-Typescript

Anvia is a TypeScript runtime for building provider-agnostic agents, tool workflows, and structured extraction inside your application code.