Python agents

YJGR Agent DNS MCP server: DNS-based agent discovery with working Bearer / OAuth2 / MCP-spec OAuth authentication. Fork of dns-aid-core.

Provider-agnostic Python AI agent framework with Bring Your Own Provider architecture

Hexagonal Architecture for Provider-Agnostic RAG Pipelines

Verifiable execution receipts for Haystack agents. Every tool call mints a verifiable AER-1 receipt at zambo.dev.

Verifiable execution receipts for LlamaIndex agents. Every tool call mints a verifiable AER-1 receipt at zambo.dev.

Verifiable execution receipts for OpenAI Agents SDK agents. Every tool call mints a verifiable AER-1 receipt at zambo.dev.

Verifiable execution receipts for smolagents agents. Every tool call mints a verifiable AER-1 receipt at zambo.dev.

Runtime for accountable AI agents: signed receipts for every action, human gates, injection defenses, hiring per proven task. Standard library only.

Client for the Zanii LLM API: OpenAI-compatible inference with a verifiable receipt for every call

A small Python agent runtime with typed tools, streaming, and on-demand skills

Add your description here

ZTAgent: Zero Trust Security for AI Agents. Never trust an agent action. Verify before execution.

Reproducible probes from a long-running AI agent society: memory injection, reasoning budgets, timeouts. Stdlib Python, pre-registered, negative results included.

Don't ask your AI to clone a website. Make it prove it. Measures how close a clone is to the original (pixels, layout, style, motion) and gives your agent the exact prompt to fix it, in a loop.

Social memory for multi-agent systems: who remembers what, about whom, visible to whom.

Agent-side A2UI chart producer for @haystackedai/a4react clients. Keep your agent (bedrock/agentcore/strands and your own biz logic are untouched); add a few lines where you already have the answer data and get a validated, drillable A2UI chart surface — richer than a hand-rolled chart. No a2ui-core wiring, catalog assembly, surface-message building or validation to write. Contract (catalogId + schemas) is baked, overridable.

ACGS rule-based tool-call governance for the Haystack Agent before_tool hook

ACLA Agentic Context Runtime: persistent project context, a deterministic Context Compiler and governed Mission Working Sets for AI agents, with lifecycle, observation, REST, UI and MCP surfaces.

CPU-first RAG retrieval for everyone. No GPU. No embedding API. No cloud bill.

Opinionated deep-agent assembly layer for Google ADK.

One-line verifiable execution receipts for AutoGen swarms. Free, no API key, offline verification, chain-head anchoring to Nostr and Bitcoin.

One-line verifiable execution receipts for CrewAI crews. Free, no API key, offline verification, chain-head anchoring to Nostr and Bitcoin.

One-line verifiable execution receipts for Haystack pipelines. Free, no API key, offline verification, chain-head anchoring to Nostr and Bitcoin.

One-line verifiable execution receipts for LangChain agents. Free, no API key, offline verification, chain-head anchoring to Nostr and Bitcoin.

AER-1 verifiable workflow receipts for LangGraph multi-agent swarms

One-line verifiable execution receipts for LlamaIndex agents. Free, no API key, offline verification, chain-head anchoring to Nostr and Bitcoin.

One-line verifiable execution receipts for the OpenAI Agents SDK. Free, no API key, offline verification, chain-head anchoring to Nostr and Bitcoin.

One-line verifiable execution receipts for HuggingFace SmolAgents. Free, no API key, offline verification, chain-head anchoring to Nostr and Bitcoin.

aesthete-agent MCP server — mechanically validated frontend aesthetics: palette library ranking, OKLCH generation, WCAG/APCA contrast, color-blind-safe data colors, theme packs, token exports (w3c/context); zero keys, zero telemetry

Aforo AI Agent Metering SDK — instrument agent runs (sessions, steps, capability calls) for billing and analytics

User access reviews for AI agents and MCP servers, with audit evidence and OSCAL output

AIMail runtime SDK (Python): gateway client, platform adapters, resources. Provisioning tools stay in the aimail repository.

Deterministic codebase architecture guardrails and topology indexer for AI coding agents

A true MCP server where the agent is the model and the API key.

九维认知空间 Agent 审计层 MCP 插件：决策步骤→九位平衡三进制状态序列→审计报告 (Audit AI agent decisions as balanced-ternary cognitive states via MCP)

Agent Auth RS 校验 SDK(spec 010 P1b):MCP 资源服务器侧 access token 校验 — aud 强校验、命名空间 sub_type 策略、kid 强制 alg、未知 kid 重取限流+负缓存、WWW-Authenticate 发现头。

Scaffold AI-agent-ready projects from curated templates, presets, or a dirtree layout

Run coding agents in rootless Podman workspace boxes

Let AI agents drive the browser tabs you already have open, by element reference, over MCP, a CLI, or Python.

Budget caps, runaway-loop detection and circuit breakers for AI agents. Zero dependencies, framework agnostic.

Protocolo de comunicacion entre agentes IA sin dependencia de tmux

Physical camera perception, measurement, and verification tool for MCP AI agents

Causal capture SDK for branching multi-agent systems

Causal capture SDK for branching multi-agent systems

Chaos engineering and self-healing recovery patterns for multi-agent LLM systems: inject hallucination loops, tool failures, cyclic dependencies and stale memory, then measure how the system degrades and recovers.

Check AI agent success claims against trace evidence instead of trusting the final message.

Local AI agent with headless browser, sandboxed shell, and plug-and-play skills

Metadata-only compatibility release forwarding agent-connector-sdk users to Scion SDK

MCP server for Django sites: tools generated from django-agent-content, for Claude Code, Claude Desktop, Cursor and other MCP clients.

Agent Control Panel SDK for Python: monitor AI agents in production and pause, resume, stop or swap their model without redeploying

Report token usage and estimated USD cost of AI agent sessions from local harness logs

Proof that AI agents' work really happened: re-runs your checks in a clean copy the agent can't edit, and writes a sealed receipt.

Shared task memory and delegation for Codex, Cursor, Claude Code, and OpenCode.

Offline scanners for the code patterns behind 68 CVEs in 9 AI-agent frameworks, plus MCP tool pinning. No dependencies, no telemetry.

Deterministic exploratory data analysis functions for LLM agents.

Local, best-effort egress observation for coding-agent sessions.

OpenAI Agents SDK adapter for Atlas Agent Engine

AI Agent 环境安全审计 CLI：供应链投毒 / 密钥暴露 / 端口暴露 / MCP server 一键体检

Check that an artifact has the digest its compliance document, SBOM or attestation names.

Offline, read-only MCP server that verifies agent evidence claims and replays the agent-evidence conformance vectors

Record brokered agent writes and check selected native reports offline

Versioned terms for claims about agent execution evidence

Lightweight production middleware for resilient LLM calls: retries, fallback routing, circuit-breaking, and rigid schema validation.

Read-only file viewer that turns a coding agent's file paths into links you can open on your phone over Tailscale

Detection validation for AI agents: replay attack traces against your detection rules and measure coverage by OWASP Agentic Top 10 and MITRE ATLAS

A runtime security and governance layer that evaluates AI-agent tool requests before they execute.

Live environmental footprint (energy, water, carbon) of AI coding agents: Claude Code, Codex CLI, Gemini CLI, OpenCode, Mistral Vibe and GitHub Copilot, computed with EcoLogits.

A production-shaped multi-agent orchestration skeleton on LangGraph with first-class tracing, retries, and token budgets.

Curated runtime skill orchestrator for AI coding assistants: plan, execute, verify.

ACGS rule-based tool-call governance for Microsoft Agent Framework function tools, via function middleware and tool approvals

BotsRated pre-payment check for Microsoft Agent Framework: function middleware that checks an x402 payTo with the free BotsRated preflight before a payment tool runs.

DuckDB vector stores for Microsoft Agent Framework.

Oracle AI Database native vector stores for Microsoft Agent Framework.

SQL Server native vector integration for Microsoft Agent Framework.

TypeSafe AI integration for Microsoft Agent Framework.

Behavior-guardrail hooks for Claude Code, Codex CLI and Gemini CLI: test-tampering + outbound-action guards, gate-liveness verification, and mutation test-honesty

A multi-agent setup for Claude Code, Cursor and Codex (orchestrator + architect, coder, grader, utility subagents) with memory-bank, jevmem and Spec-Driven Development wired in, installed into a project with one command.

Contract tests for agent handoffs: record what one agent returns, infer what the next one reads, and check it in CI without LLM calls.

Inventory and clean up what coding-agent CLIs (Codex, Claude Code, Cursor, Gemini, ...) leave behind on macOS and Linux.

Reserved for the Agent Interface Model (AIM) specification. Not yet released.

Failover and credential-routing layer for AI agent stacks: probe agents with real requests, classify failures with a zero-token gate, switch on collapse, fail back on recovery.

Read-only checker for Kubernetes AI-agent workloads: flags missing gVisor/Kata runtime class, token automount, root or privileged containers, host namespaces, missing limits and missing metadata/RFC1918 egress NetworkPolicy.

Keep Claude Code and Codex from overwriting each other's work: hook-enforced path leases, presence and a shared message log over MCP.

Measures what an agent tool definition loses when converted between MCP, OpenAI, A2A, Anthropic, Gemini, Bedrock and 10 more formats. Computed, not asserted.

SPIFFE/mTLS MCP client for Claude Desktop — no local agent needed

Shared, git-backed memory for Claude Code and Codex.

Money primitives, fee curves, and reference-bound paywalls for AI agents

Pluggable secure-agent platform for Agent Nebula-compatible agents.

Standards-oriented security SDK for Agent Nebula and Agent Genesis

Configuration-driven Python facade for building secure A2A agents on Agent Nebula Platform

Installable A2A and A2UI examples for Agent Nebula SecureAgent

Local terminal and web dashboard for AI agent sessions, MCP calls, OpenTelemetry traces, and errors.

Which files did two of your coding agents write within the same hour? Read from your local git log.

Runtime-grounded control plane for durable Codex Agent and Operator sessions.

A project launcher and shared context for Codex, Claude Code, and GitHub Copilot CLI.

Lightweight multimodal agent skill to inspect and understand Instagram Reels, TikTok, and YouTube Shorts (audio + keyframes + timeline)

Regression testing for stochastic AI agents: frozen experiments, fault injection, replayable reduced failures.

Process-metadata labels for OpenTelemetry agent spans

Scaffold launch-ready, AI-agent-friendly open-source repositories.

Hello world package for Agent RT.