Skip to main content

Meshagent

Project description

Meshagent

MeshAgent Python SDK

MeshAgent is your platform to create, deploy, and manage AI agents collaboratively and at scale, securely and in real time.

MeshAgent removes the infrastructure headaches of building and shipping AI Agents. It spins up secure, real-time "Rooms" that connect humans, agents, and shared context -- letting you launch, share, and refine agents in hours instead of weeks.


Documentation: docs.meshagent.com

Website: www.meshagent.com

MeshAgent Studio: studio.meshagent.com


Why MeshAgent?

  • Real-time multi-user "Rooms" for true human-AI teamwork: Secure workspaces, "Rooms", automatically spin-up when someone joins, tracking presence, chat, documents, and agent activity, and disappear when everyone leaves -- so people and agents stay in sync.

  • Accelerated feedback loop and shortened development cycle: Invite a colleague or stakeholder into the MeshAgent Studio Room so they can see, hear, and interact with your agent immediately -- letting you demo, gather feedback, and iterate on the agent on the same day.

  • Shareable links that showcase your agent: After you deploy an agent, MeshAgent provides you a URL so colleagues or customers can jump straight into the Room, try the agent, and give feedback -- no code checkout, IDE, or GPU required.

  • Reusable and extensibly agent tools: MeshAgent ships prebuilt, reusable toolkits for common Room interactions (e.g., file and document handling, media generation, dynamic UI interactions) and high-demand tasks (e.g., web search or document-to-Markdown conversion). Support for custom tools and the Model Context Protocol (MCP) enables you to seamlessly integrate any MCP-compatible service into a Room without changes to your applications. Tools are centrally managed like agents, allowing you to deploy them once and reuse them effortlessly.

  • Built-in Observability: Streaming logs and traces give you real-time insight into every message, agent action, and error.

  • Secure and elastic by default: Project-scoped keys, on-demand provisioning, and auto-scaling infrastructure keep Rooms private, secure, and ready for your usage needs.

  • Support across languages: The same feature set (Rooms, Agents, Tools, Messaging, Queues, Storage, Documents, etc.) is exposed through official Python, Javascript, Typescript, and Dart SDKs, so every team member can work in their preferred language.

Getting Setup

Follow our Getting Started Documentation to setup your MeshAgent account, create your first project, and start building agents!

Next Steps and Examples

To see examples of agents in action and to start building your own agents check out the MeshAgent docs at docs.meshagent.com

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

meshagent-0.5.15.tar.gz (7.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

meshagent-0.5.15-py3-none-any.whl (7.1 kB view details)

Uploaded Python 3

File details

Details for the file meshagent-0.5.15.tar.gz.

File metadata

  • Download URL: meshagent-0.5.15.tar.gz
  • Upload date:
  • Size: 7.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.3

File hashes

Hashes for meshagent-0.5.15.tar.gz
Algorithm Hash digest
SHA256 24695d5a531e26c0b1c80373097fa9a8d46f78e8aa1500fadd7a1122f92a126b
MD5 e32d95a0f5b0f2a7ce9aead904ccca4a
BLAKE2b-256 a0eff46d35032a7f087123af2e4eb9961616b3ecfb6386185d53d265d30e05bc

See more details on using hashes here.

File details

Details for the file meshagent-0.5.15-py3-none-any.whl.

File metadata

  • Download URL: meshagent-0.5.15-py3-none-any.whl
  • Upload date:
  • Size: 7.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.3

File hashes

Hashes for meshagent-0.5.15-py3-none-any.whl
Algorithm Hash digest
SHA256 6492f80f8defff81fd7f5cfbca881d316a3a7f0b3452079a980ddcf47ab3c556
MD5 9bd846f46a99e53a073226958e638a5c
BLAKE2b-256 fb5bcbfe1e5fbee74811fc58204a79214ad9cb2b73985cac95b3349a6880cbbc

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page