agent-client-protocol
A Python implement of Agent Client Protocol (ACP, by Zed Industries)
Decision gist · record as of 2026-08-14
Yes, if you are building or integrating agents with the ACP specification. The package is actively maintained, has low install friction, includes comprehensive examples, and provides the schema bindings and transport plumbing needed to avoid reimplementing the protocol. Verify the license status before adopting in a restricted-license context.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later (supports up to 3.14); asyncio event loop required for transport operations.
- Low friction install with a single runtime dependency (pydantic).
- Active maintenance with a release 13 days ago and recent commits; repository is not archived and has 304 stars.
License · maintenance · safety
(unclear) — License status is unclear—no SPDX identifier or raw license text is recorded in the package metadata. Verify the actual license terms before adopting in a commercial or restricted-license context.
last release 2026-08-01 (13 days) · last repo commit 2026-08-13 · 304 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 34,506,071 downloads/mo, #757 on PyPI
Alternatives
Verify before relying
pip install agent-client-protocol
import agent_client_protocol
# See examples/ directory for runnable agent and client patterns- Whether the license is actually open-source or proprietary—metadata shows 'unclear' treatment with no SPDX or raw license field.
- Whether Gemini bridge and permission flow examples are production-ready or experimental demonstrations.
- Stability guarantees for the generated schema models as the upstream ACP spec evolves.
- Concrete API surface and which classes/functions are the primary entry points for agent and client builders.
What it is and what it does
Agent Client Protocol (ACP) is a specification for building interoperable agents and clients. This package provides a Python implementation with generated Pydantic models that track the upstream ACP schema, async base classes for custom agents, stdio JSON-RPC transport plumbing, and helper builders. It also includes contrib utilities like session accumulators and permission brokers drawn from real deployments.
The package is designed for three audiences: agent authors building ACP-compatible assistants with typed models and event-stream ergonomics, client integrators embedding ACP parties inside Python applications or wrapping CLIs via stdio, and tooling teams experimenting with permission flows or streaming UX without reimplementing transports. The repository includes runnable examples covering streaming, permissions, Gemini bridges, and duet patterns, plus a quickstart guide and documentation hub.
Use it for
- Build a custom AI agent that speaks the ACP protocol and integrates with editor tooling.
- Wrap an existing CLI tool as an ACP client using stdio JSON-RPC transport without writing transport code.
- Implement permission brokers or session accumulators for multi-turn agent interactions.
- Prototype streaming UX patterns or permission flows using provided examples.
- Generate type-safe request/response payloads that stay valid as the ACP schema evolves.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building or integrating agents with the ACP specification.
The package is actively maintained, has low install friction, includes comprehensive examples, and provides the schema bindings and transport plumbing needed to avoid reimplementing the protocol. Verify the license status before adopting in a restricted-license context.
Install
agent-client-protocol on PyPI
Before you install
Low friction install with a single runtime dependency (pydantic). Active maintenance with a release 13 days ago and recent commits; repository is not archived and has 304 stars.
Requires Python 3.10 or later (supports up to 3.14); asyncio event loop required for transport operations.
License in practice
License status is unclear—no SPDX identifier or raw license text is recorded in the package metadata. Verify the actual license terms before adopting in a commercial or restricted-license context.
Quickstart
pip install agent-client-protocol
import agent_client_protocol
# See examples/ directory for runnable agent and client patternsVerify before relying
- Whether the license is actually open-source or proprietary—metadata shows 'unclear' treatment with no SPDX or raw license field.
- Whether Gemini bridge and permission flow examples are production-ready or experimental demonstrations.
- Stability guarantees for the generated schema models as the upstream ACP spec evolves.
- Concrete API surface and which classes/functions are the primary entry points for agent and client builders.
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release <3.15,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 1 packagepydantic |
| Maintenance | Actively maintained 13 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 34,506,071 / month, #757 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: DevelopersProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Software Development :: Libraries :: Python Modules |
Evidence: agent_client_protocol-0.12.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “acp sdk python”
- agent-client-protocolProvides Python models, async transports, and helper utilities for…
- deepagents-acpBridges Deep Agents with the Agent Client Protocol (ACP) to run AI…
- jupyter-ai-acp-clientProvides a JupyterLab extension that integrates Agent Client Protocol…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also deepagents-acp · pyatlan · jupyter-ai-acp-client · a2a-sdk · fast-agent-mcp · toolbox-adk · a2ui-agent-sdk · agent-framework-a2a · google-adk · microsoft-agents-activity