Agent Infrastructure Python Packages

inkbox

SDK, skills, and examples for Inkbox: give AI agents a persistent identity with email, phone number, and internet address

aimeat-crewai

Open protocol and reference node where humans, their AI agents, and local LLMs share apps, knowledge, and capabilities. Self-hosted, federated, MIT.

contextweaver

Budget-aware context compilation and context firewall for tool-heavy AI agents.

synapse-layer

MCP-native infrastructure for persistent AI agent memory with encrypted storage, semantic retrieval and cross-agent continuity.

chainweaver

Deterministic MCP tool flows for AI agents. Remove unnecessary LLM calls between predictable tool steps.

safeagent-exec-guard

Execution control layer for AI agents — prevents duplicate or incorrect real-world actions under retries, uncertainty, and stale context.

crewplane

A control plane for resumable coding-agent workflows.

cross-validated-search

Search infrastructure for AI agents: free by default, MCP-ready, LLM-context aware, and production-grade when needed.

memee

Cross-model shared memory for AI agents. One canon every model reads. Free OSS via pipx install memee. memee.eu hosts the Team edition with shared scope, SSO, audit log.

pyshal

Turn your whole lab — hardware and software — into safe, typed, permission-gated tools for an AI agent.

etchplan

Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.

mcp-preflight

Inspect, fingerprint, and diff an MCP server’s declared capability surface.

mitos-run

Millisecond microVM sandbox forking for AI agents on Kubernetes. Firecracker VMs that restore from memory snapshots in milliseconds, fork a running VM into N copies, and persist durable, versioned workspaces. Self-hostable, declarative CRDs.

octopus-linkedin

Governed LinkedIn marketing over MCP — draft, review, publish, comment, and AI-write (Anthropic/OpenAI/Gemini) via the official LinkedIn API. MCP server + CLI.

aegize

Infrastructure for autonomous AI agents: identity, policy, permissions, approval workflows, and audit.

mcp-surfaceprint

Inspect, fingerprint, and diff an MCP server’s declared capability surface.

sitepulsar-mcp

Hosted MCP server for SitePulsar — Agent Experience Optimization (AEO) tools that measure and improve how findable, readable, and usable any website is to AI answer engines and autonomous AI agents.

rebuno

Python SDK for the Rebuno execution runtime

zero-api-key-web-search

Search infrastructure for AI agents: free by default, MCP-ready, LLM-context aware, and production-grade when needed.

darwin-agentic-cloud

Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README

atomicmemory-langflow

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

courier-agent-email

Temporary email inboxes for AI agents. Receive OTP codes, magic links, and verification emails. No signup. Zero dependencies.

report-needs

MCP server for AI agents to report infrastructure needs. What do agents actually need? Let them tell you.

nightona-toolbox-api-client-async

Open-source continuation of Daytona — secure, elastic sandbox infrastructure for AI code execution and agent workflows. Community fork of the last AGPL-3.0 release (v0.190.0).