Skip to content
Alternatives
Software like Agent P
What else does this job. Matched on what each project does, not on who links to whom.
Closest first
- Agent Web Protocolagentwebprotocol.orgAgent Web Protocol (AWP) is an open standard designed to make websites accessible and understandable to AI agents by defining a single machine-readable manifest, agent.json, placed at the root of a website. This file communicates a site's available capabilities, supported agent protocols, and authentication methods, allowing agents to interact with web surfaces without the need for scraping or guesswork. The protocol draws a parallel to previous web standards like robots.txt and schema.org, offering a declarative approach for the era of AI agents. The agent.json manifest allows websites to specify their intent and enumerate structured actions—such as search or purchase—with typed parameters, HTTP methods, and endpoints. With version 0.2, the manifest can declare compatibility with multiple agent protocols, including MCP, A2A, AP2, x402, and others, enabling a single site to communicate its support for various agent standards in one place. The manifest also includes a protocols block and a via field to route actions through the appropriate agent protocol. Authentication options supported by AWP include OAuth 2.0, API keys, bearer tokens, and session-based authentication, with explicit scope declarations possible for each action. AWP is intended for developers and site operators who want to make their web properties agent-ready. The manifest format is based on a JSON schema, making it straightforward for both agents to parse and humans to author. Tooling is provided via the npx agent-json command-line tool, which can generate new agent.json files or validate existing ones from local files or remote URLs. There is also support for Claude Code integration through the AWP MCP server. The protocol is community-driven, with its specification, validator, and reference implementation all open-source and MIT-licensed. Development takes place publicly on GitHub. Live deployments, such as the LaClawClaw Shopify store, showcase AWP in production, with manifests that declare multiple protocols and payment options. By standardizing how websites expose their capabilities to agents, AWP aims to facilitate seamless machine interaction across the web.
- Agent Tool Protocolagenttoolprotocol.comAgent Tool Protocol (ATP) is a protocol designed to enable AI agents to write and execute code directly, rather than relying on predefined tool calls. It addresses challenges encountered in traditional server protocols like MCP, which require developers to build gateways that aggregate multiple services and manage complex stateful connections. com's MCP gateway, drawing on experience with large-scale API integrations and developer infrastructure. A central feature of ATP is its approach to code execution for AI agents. Instead of loading all available tools into an agent's context before reasoning begins, ATP allows agents to dynamically search for and use only the relevant APIs as needed. This reduces unnecessary context bloat and improves efficiency. The protocol leverages the OpenAPI standard for REST APIs, enabling agents to interact with well-defined endpoints and schemas, and to compose operations such as filtering and mapping data through code execution. ATP incorporates several layers of security and control to address the risks associated with code execution. Code runs in an isolated environment with no access to the file system, network, or environment variables, mitigating the risk of data exfiltration or unauthorized access. APIs can be annotated as destructive, sensitive, or safe, and there are explicit controls to allow or block specific endpoints. For operations that could alter or delete data, ATP supports human approval workflows, ensuring that critical actions require explicit authorization. The protocol also supports advanced agent architectures, including multi-level agents that can spawn sub-agents for parallel processing of tasks. This flexibility is intended for developers building scalable and secure AI agent systems that need to aggregate and manage multiple APIs efficiently. ATP is positioned within the frameworks and SDKs class, focusing on enabling dynamic, code-based API composition for AI agents.
- Introductionagentclientprotocol.comThe Agent Client Protocol (ACP) is a standardized protocol designed to facilitate communication between code editors or integrated development environments (IDEs) and coding agents. Its primary aim is to address the challenges of interoperability between editors and agents, which traditionally require custom integrations for each pairing. By introducing a common protocol, ACP enables agents and editors to work together without the need for editor-specific APIs or agent-specific interfaces, reducing integration overhead and broadening compatibility. This protocol is intended for scenarios where developers primarily use their code editor and wish to leverage external agents to assist with coding tasks. ACP supports both local and remote agent configurations. Local agents operate as sub-processes of the editor and communicate using JSON-RPC over standard input and output streams. For remote agents, communication occurs over HTTP or WebSocket, although full support for remote agents is still under development. The protocol reuses JSON representations from MCP where applicable and introduces custom types tailored to agentic coding user experiences, such as the ability to display code diffs. Markdown is the default format for user-readable text, chosen for its flexibility in representing rich formatting without requiring editors to render HTML. ACP decouples the development of editors and agents, allowing each to innovate independently. Editors that implement ACP gain access to a broader ecosystem of agents, while agents that support ACP become compatible with any editor that adopts the protocol. This approach aims to give developers greater freedom in choosing their tools and to minimize lock-in to specific platforms or interfaces. The protocol is being developed in collaboration with agentic platforms to ensure it meets the requirements of both local and cloud-hosted deployment scenarios.
- Auto Agent Protocolautoagentprotocol.orgAuto Agent Protocol is an open standard that enables AI assistants to interact with automotive dealerships through structured, typed messages. It covers inventory search, dealer information, and lead submission, facilitating seamless integration with dealer CRMs and compliance with industry standards. The protocol is designed for developers building AI-driven automotive solutions.
- AI Agentaiagent.appAI Agent provides a no-code platform for creating and deploying autonomous AI agents that handle complex tasks such as research, report generation, and workflow automation. Agents can connect to tools like GitHub, Gmail, Notion, and Linear, use company documents for context, plan multi-step processes, and execute actions with minimal human oversight. It enables teams to multiply productivity by delegating routine work to intelligent software agents.
- TheProtocoltheprotocol.cloudTheProtocol is self-hosted infrastructure for AI agent economies, providing decentralized identities, federated registries, token balances, payments, reputation, and an immutable event ledger. Developers can install its Python SDK, run sovereign registries, and connect services through SPIFFE/SPIRE mutual TLS.
- agentprocpypi.orgagentproc is an open-source protocol SDK and CLI that allows developers to connect any agent CLI to various messaging platforms. It provides a unified protocol for agent integration, making it easier to bridge command-line agents with chat or messaging systems. Ideal for developers building agent-based workflows or integrations.
- Introductionag-ui.comAG-UI is an open, lightweight, event-based protocol for connecting AI agents to user-facing applications. It is described as a general-purpose, bi-directional connection between a user-facing application and an agentic backend, intended to help application developers build reliable, debuggable, user-friendly agentic features while avoiding complex ad-hoc wiring. Its documented building blocks include live token and event streaming for multi-turn sessions with cancel and resume, typed attachments and real-time media for files, images, audio, and transcripts, and stable typed components for rendering model output under app control. The protocol also supports a small declarative language for generative UI, where agents propose trees and constraints and the application validates and mounts them. Other listed capabilities include shared state with streamed event-sourced diffs and conflict resolution, visualization of intermediate reasoning from traces and tool events, typed handoffs for frontend tool calls, backend tool output rendering, human-in-the-loop interrupts, nested sub-agents with scoped state, real-time user steering, tool result and log streaming, and custom events. The documentation frames AG-UI as one of three open agentic protocols, alongside MCP and A2A, and says it is the Agent–User Interaction standard. It is built on HTTP and WebSockets. Supported integrations shown on the page include direct-to-LLM, agent framework partnerships, first-party agent frameworks, and community agent frameworks, and the page states that AG-UI was born from CopilotKit’s initial partnership with LangGraph and CrewAI. The documentation also points to SDKs in TypeScript, Python, and .NET, plus a Discord community and an AG-UI repository. The page does not state pricing or licensing details.
- agentpubagentpub.orgAgentPub is an open research platform designed for AI agents to write, peer-review, and cite academic papers. The platform enables autonomous AI agents to engage in the full research publication process, from generating and submitting papers to reviewing and discussing agent-generated research. All published papers on AgentPub are freely accessible, supporting an open approach to scholarly communication. The platform offers both a Python SDK and a REST API, allowing users to integrate their AI agents for automated research, writing, and submission of academic papers. In addition to publishing, AgentPub provides features for exploring citation graphs, making it possible to track relationships between papers and follow AI research trends. The service is oriented toward those developing or employing AI agents capable of autonomous research activities, as well as those interested in monitoring the outputs and interactions of such agents within a scholarly context. 0 license. The platform is attributed to Martin Smit. By focusing on AI-driven research publication and peer review, AgentPub addresses the emerging need for infrastructure that supports agentic contributions to scientific literature.
- Agent Client Protocolagentclientprotocol.comAgent Client Protocol (ACP) defines a standardized way for AI agents to interact with client applications, enabling capabilities like file access, code editing, and UI control. Version 2 is currently in draft with updated schemas, stabilized options, and SDKs reaching 1.0. It is backed by organizations including Zed Industries and JetBrains and includes comprehensive documentation for implementers.
- agentaogithub.comagentao is an open-source governed agent runtime designed for running AI agents locally with a focus on privacy and embeddability. It supports multimodal agents, integrates with MCP, and is suitable for developers building private, local-first AI solutions.
- agentdossieragentdossier.aiagentdossier is an open-source Python SDK designed to help developers manage provenance, records, and anchoring for AI agent systems. It provides tools for tracking agent actions and maintaining reliable records, supporting transparency and auditability in agent-based workflows.
- AgentCard.orgagentcard.orgAgentCard.org is a platform and infrastructure layer for the agentic web, enabling developers to discover, validate, and run AI agents across multimodal workflows. It offers tools for agent readiness, metadata, and unified runtime for AI agent deployment.
- OpenAGPopenagp.ioOpenAGP is an open, vendor-neutral protocol designed to standardize governance and auditing for AI agents across multiple vendors. It addresses the challenge enterprises face when managing hundreds of AI agents from different providers, each with their own audit formats, policy enforcement mechanisms, and identity models. By defining a unified approach, OpenAGP enables organizations to enforce a single policy and maintain a verifiable audit trail regardless of the agent vendor, much like how SAML standardized identity management. At its core, OpenAGP specifies a set of signed, schema-defined messages exchanged between a customer's governance plane and an agent vendor. These messages allow for consistent policy enforcement and the creation of a tamper-evident, hash-chained ledger of agent actions. Events and policies are signed using Ed25519 and canonicalized with RFC 8785 (JCS), ensuring that they are independently verifiable. The protocol supports three main flows—events, policy, and decision—corresponding to different levels of vendor conformance (L1, L2, L3). At the basic level, vendors emit signed canonical events for passive observability. Higher levels add support for accepting and applying customer policies and real-time decision callbacks, enabling human-in-the-loop governance for high-stakes actions. OpenAGP is intended for a range of stakeholders. Vendors can quickly implement the protocol using reference SDKs and prove conformance with a dedicated suite. Customers benefit from authoring governance policies once and having them enforced across all conformant vendors. Auditors gain access to standardized, signed artifacts that can be verified independently, without having to trust any intermediary. Contributors are invited to participate in shaping the standard through an open RFC process, with free SDKs and no contributor license agreement required. The protocol is available as an open specification, with reference implementations in Python, TypeScript, and Go. 0 for SDKs, and CC0 for registry data. OpenAGP is maintained by its community and aims for multi-stakeholder governance as it matures.
- Agent-Nativeagent-native.comAgent-Native is an open-source framework for agentic apps. It is described as a way to build applications with agents at the core, so developers do not have to choose between apps and agents; the site says Agent-Native apps are both. The framework is presented for building SaaS tools, internal tools, and other agent-first applications. A central feature is its action model: one operation can become a UI action, an agent tool, an HTTP endpoint, an MCP/A2A surface, a CLI command, a scoped permission check, and an audit trail. The documentation and examples also mention notifications, recurring jobs, agent teams, monorepos, permissions and RBAC, organizations, workspace secrets, docs search, source search, context awareness, observability, real-time sync, SQL state, multi-tenancy, data loaders, live queries, agent instructions, provider grants, comments, review links, privacy controls, skills, security, audit logs, workspaces, voice input, generative UI, tool calls, shared actions, i18n, MCP auth, external agents, A2A handoffs, human handoff, durable resume, sharing and privacy, real-time collaboration, SSO, OAuth, MCP servers, scoped access, DB adapters, approvals, automations, governance, jobs, AG-UI dispatch, background runs, rate limits, queues, cron schedules, analytics, experiments, feedback loops, file uploads, evals, app skills, provider APIs, app web surfaces, one-click forks, local file mode, memory, webhooks, self-editing code, schema migrations, hosted deploys, environment setup, OAuth callbacks, exports, and dashboards. The site includes several example apps built with the framework, including Clips, a Loom-like app with browser debug capture, calendar-synced meeting notes, voice dictation, transcription, summarization, search, and agent editing; a visual plan mode for Codex, Claude Code, and coding agents; a design studio for Figma-style prototyping; a Markdown and MDX content app for local files; a Slides app for generating presentations from prompts; an analytics app that connects to any data source and lets the agent write SQL and generate visualizations; and a minimal ChatGPT-style app. The framework can be used from its docs or through Builder.io, and the page shows an npx create command for starting a new app. It also links to GitHub, Discord, npm, and a docs search interface. The site describes the framework as open source, forkable, and yours.
- Agent.soagent.soAgent.so is a web platform that allows users to chat with hundreds of AI agents, create their own custom agents, train them with data, and assign skills for various productivity and automation tasks. It is designed for users seeking to leverage AI for personal or business efficiency.
- AGENTISagentisexchange.comAGENTIS is an infrastructure platform for AI agent commerce. Its homepage describes it as providing escrow, reputation, and dispute resolution for the autonomous economy, with a central theme of giving an AI agent a wallet, a marketplace, and a reputation. The platform includes an agent directory, block explorer, oversight dashboard, agent evaluations, a vault dashboard, guild workspace, and futures trading. It also offers developer tooling through a Python SDK, quickstart guide, API documentation, API playground, no-code builder, agent templates, and a builder directory. The site says agents can register with one API call, receive an instant API key, build a profile with skills, portfolio, and gig packages, earn verified badges, and then engage and deliver work while building reputation. It also states that operators can submit details about an AI fleet, complete personal onboarding and identity verification, and manage all agents from a single operator dashboard. AGENTIS also advertises persistent, cross-machine memory, shown in a Python example that includes memory_write, and says it supports REST and MCP integration. The page lists 400+ API endpoints, 23 MCP tools, and integrations with Claude, GPT-4, Gemini, and Cursor. It also mentions a live dashboard, live metrics, and a review process for operators intended to protect counterparties and maintain platform integrity. The platform is described as live since 15 March 2026 and as SA-based and POPIA-compliant. Pricing is split between free access for agents and subscription tiers for operators. Listed operator tiers include Explorer Free, Builder R299 per month, Professional R999 per month, and Enterprise R2,499 per month, with varying agent registrations, transaction limits, vault storage, commission rates, and support levels. Agent subscriptions are also offered, including AgentHub Basic Free and AgentHub Pro at R36 per month. Additional paid storage tiers and add-ons are listed, and the pricing section states that all paid tiers offer a 20% discount for annual prepayment. The page also says 10% of all platform commission is allocated to a charitable fund.
- AAPaap-protocol.devAAP, the Agent Accountability Protocol, is an open standard designed to provide a foundational accountability layer for autonomous agents. It addresses the gap left by existing agent communication protocols, which do not specify who authorized an agent's actions, who is responsible, or how to prove accountability. The protocol is aimed at developers building agent infrastructure or frameworks who require verifiable mechanisms for identity, provenance, authorization, and audit in autonomous systems. AAP defines four core primitives. First, it assigns each agent a unique, verifiable URI, structured as aap://org/type/name@version, and backed by an Ed25519 keypair for cryptographic verification. Second, it establishes provenance through a SHA-256 artifact chain, ensuring that every output is traceable to its origin, including the model, version, parameters, and timestamp. Third, the protocol introduces a five-level autonomy scale for authorization, with a specific rule that physical systems cannot exceed level 3 autonomy—this restriction is hardcoded and enforced via eBPF, making it non-overridable. Finally, AAP implements a tamper-evident audit chain: every agent action is signed and stored locally, forming a hash chain that can be verified by anyone at any time. The protocol is delivered as an open standard under the MIT license, with a reference SDK available for rapid implementation. Developers can install the SDK using Python's package manager and utilize provided classes to create agent identities, record auditable actions, and verify tamper-evidence. The reference implementation, Halyn, extends AAP with features such as a governance layer, proxy, filesystem hooks, process isolation, audit chain, and dashboard. AAP's specification is concise, fitting in a single Markdown file, and it is intentionally designed without vendor lock-in, requiring no cloud dependencies. AAP is positioned as a complementary protocol to existing agent communication standards, focusing solely on accountability rather than communication. Its open, MIT-licensed nature and emphasis on verifiable agent actions make it suitable for developers and organizations seeking to build trustworthy autonomous agent systems.
- agt-agentpypi.orgagt-agent is an open-source AI agent framework for developers and researchers, featuring a multi-model ReAct engine, Model Context Protocol (MCP) integration, Coze workflow support, and a web-based visual editor. It enables rapid development and orchestration of autonomous AI agents with flexible workflows.
- aimarket-agentpypi.orgaimarket-agent serves as a reference implementation of a consumer agent for the AIMarket Protocol v2. It allows AI agents to discover other AI services, handle payments, and invoke them programmatically. Designed for developers building AI-to-AI marketplaces or autonomous agent ecosystems, the library is open source under the MIT license.
- agentdefpypi.orgagentdef is an open-source CLI tool and specification for defining AI agents in a portable, framework-agnostic way. It enables developers to standardize agent definitions and streamline deployment across different AI frameworks.
- AgentGraphagentgraph.coAgentGraph is a web-based platform that provides verifiable identity, auditable trust scores, and a decentralized social graph for both AI agents and humans. It helps users discover, connect, and collaborate securely in AI-driven environments.
- air-agentgithub.comair-agent is an open-source Python framework for building lightweight AI agents with support for OpenAI tool calling, Model Context Protocol (MCP), and parallel subagents. It is designed for developers who want to orchestrate and extend AI agent capabilities efficiently.
- Agentcygoagentcy.comAgentcy is a hosted AI agent for marketers that connects to various marketing data sources and provides actionable insights. It integrates with tools like Claude, ChatGPT, and others, streamlining analytics and reporting for marketing teams.
- AgentOvenagentoven.devAgentOven is an open-source enterprise agent control plane for managing AI agents. It combines a central agent registry, model routing, RAG pipelines, workflow orchestration, observability, and native A2A protocol support in one system. The site also describes it as the open-source Kubernetes for AI agents. Its feature set includes registering, versioning, and discovering agents with rich metadata, along with first-class support for Google’s Agent-to-Agent protocol. Agent routing can span OpenAI, Anthropic, Azure, Bedrock, and local models, with fallback chains and cost caps. Other named capabilities include version-controlled prompt management with variable interpolation, A/B testing, and rollback, declarative DAG-based workflow orchestration with chaining, conditions, fan-out and fan-in, pause and resume, real-time token and API cost tracking with budget alerts and quotas, and OpenTelemetry-native distributed tracing, metrics, and structured logging. It also supports native MCP integration, zero-downtime blue/green deploys, auto-scaling, health checks, canary rollouts, built-in vector search, five retrieval strategies for RAG, and enterprise data connectors for Snowflake, Databricks, and S3. Delivery is through a CLI and SDKs. The page shows agentoven-cli commands, an initialization flow that creates agentoven.toml and prompts/system.md, and SDKs for Python, TypeScript, and Rust. The architecture is described in layers, from SDKs and CLI through protocol and control-plane layers to infrastructure components including PostgreSQL, pgvector, Redis, OpenTelemetry Collector, and Prometheus/Grafana. Example code shows registration, baking an agent, and sending a task through A2A. The site also says the tool works with LangChain in the example and refers to workspace isolation through a kitchen model. AgentOven is open source and MIT licensed. The page presents it as built for teams and organizations that need a single control plane for agent registry, routing, workflows, RAG, observability, cost tracking, and governance.
- agentpkpypi.orgagentpk is an open-source CLI tool that allows developers to package AI agents into portable .agent files, making it easier to distribute and deploy agents across different environments. It is designed for AI developers and researchers who need a standardized way to share agent implementations.
Ranked by how close each one sits to Agent P in the index, not by popularity. Back to Agent P →