Python agents

MCP server for x402 micropayments — query paid APIs with autonomous USDC payments on Base

RAG pipeline sederhana pakai OpenRouter dan ChromaDB

Local Unified Harness runtime and native bindings for Vibe

Portable contracts and loop gates for AI coding agents

MOSS Agent Runtime SDK - real-time governance for AI agents (interception, signed events, heartbeat, offline revocation, kill switch)

Drop an NGS file, get a plain-language answer with receipts: FastQC/MultiQC quality control, run-folder audit, pipeline-log diagnosis

Python client library for connecting to and communicating with AI Agents that implement the Agent2Agent Protocol (A2A), spec v1.0.1

Suppress helpdesk welcome emails in response to auto-generated emails

Allows to use server environment with storage backend S3

Live prefill/decode progress for a local Ollama server and basic observability metrics

Run OpenAI Agents SDK sandboxes on opsen - machine, model and tool spend on one bill.

可扩展的多向量数据库接入库（redis-search / milvus / milvus-lite / pgvector / elasticsearch / sqlite-vec / qdrant），集成 embeddings 与 rerank 模型，支持二阶段召回及插入、删除、刷新等管理功能。

Unified blob storage abstraction for Oridecon Framework - S3, GCS, Azure Blob, and local filesystem

A short description of my modern Python project

Multi-model AI orchestrator built on the nexus brain. Multi-model routing, ReAct pipeline, plan mode, custom slash commands, subagents.

Deterministic policy-authority kernel for autonomous agent payments.

A pytest plugin for regression-testing LLM applications: metamorphic relations and flakiness statistics.

Synthetic product search relevance and ranking agent

Observability and drift detection for multi-agent systems (AutoGen, LangChain/LangGraph)

LiteLLM provider backend for purrcept_core.

pydantic-ai tool integration for Algenta: a governed-execution-aware toolset wrapping a self-hosted Algenta engine's MCP tool surface

Agent Execution Evidence for Pydantic AI, by Sentience Governor

Run Pydantic AI agents on opsen — machine, model and tool spend on one bill.

Use your Claude Code subscription from a Pydantic AI Agent or CLAI2, with full tool support

Vietnam Quantitative Trading and Market Data Agent

LLM Router – core library with optional API and metrics

Plugins for the LLM Router (guardrails, maskers, etc.)

Generic, reusable Helm chart for deploying arbitrary services to Kubernetes — not RagLeap-specific

An open source observability RAG framework.

Local one-shot YAML/JSON agent workflow engine + MCP toolkit (BYOK).

agent tasks for Render Workflows

Simple and reusable S3 file upload/delete utilities for Python applications.

Decision breakdown point (k*) and ranking-fragility diagnostics for forecast model selection

AI agent tools over x402 micropayments (HTTP 402, USDC/Base) - Python client, MCP server, free previews.

Smithy RPA agent - runs on Windows machines and executes processes dispatched by a smithy-cloud orchestrator

Sovereign Agent Stack — A local-first, compile-time AI agent framework

Speechmatics Agent STT Python client for agent transcription

SDK for building agents that integrate with the STELLA platform

Database compression system evolving per-column encoding recipes and a molecular (DNA) storage layer.

CLS observability SDK for LangChain/LangGraph — 6-layer span hierarchy, direct upload to Tencent Cloud CLS

Minimal multi-provider agent library with tools

Emit a Testimony Record from an AutoGen workbench, so the record can say who approved an action and what was refused.

Emit a Testimony Record from a CrewAI crew, so the record can say who approved an action and what was refused.

Emit a Testimony Record from an OpenAI Agents SDK run. The SDK has the approval gate; this makes the record say who opened it.

Emit a Testimony Record from a Pydantic AI run. Their approvals accept a bare bool; this requires a person and a source for that person's identity.

Reserved distribution name for the Tiny-LLM systems course

TjAgentForge CLI Agent — local executor that proxies your local git repos (branch / apply patch / commit / push) with source code never leaving your machine.

Type annotations for aiobotocore AgentRegistry 3.10.0 service generated with mypy-boto3-builder 8.12.0

Type annotations for aiobotocore AgentRegistryControl 3.10.0 service generated with mypy-boto3-builder 8.12.0

The Vis Python SDK — author extensions and control local or remote engines.

Point vLLM (or any OpenAI-client-based consumer) at Algenta's own OpenAI-compatible /v1/chat/completions and /v1/responses surface -- a thin base-url/api-key helper plus a real, honest capability-fidelity conformance suite

Low-downtime hot migration for vLLM inference services, via monkey-patching and a plugin (no vLLM source changes).

Out-of-tree speculative decoding plugin for vLLM-HUST on Ascend

Security scanner for AI-agent skills: audit every SKILL.md on your machine for malware, prompt injection, and secret exfiltration. Deterministic static analysis (with an optional LLM layer) for Claude, Cursor, and MCP skills — like npm audit / semgrep, but for agent skills.

Fail-open reliability monitoring for unattended agent jobs

A vLLM-style, production-grade LLM inference server built natively for Windows (single GPU, single machine)

TUI agent that drives your Edge browser via CDP to auto-produce WeChat article layouts on xiumi.us (command: xiumi)

Modern, deterministic Adaptive Cards from small, forgiving agent tool calls

Renamed to Tracyn -- pip install tracyn instead. See https://tracyn.online

A LangChain-MCP powered app for education.

A robust three-tier LLM-aware caching SDK using Redis, ChromaDB, and automatic SQLite bootstrap.

Codex session manager: login, launch, rollover, and a shared web console via abstract-serve-core.

CrewAI tools and integration for the Adam Network autonomous agent message stream

Official Aeon brand name - the open-source autonomous AI agent framework. See https://www.aeon.fun

Deterministic archive and backup service for AI interaction histories.

Leave-one-out ablation testing, backward elimination, and ROI evaluation for multi-agent decision systems — find out which agents' findings actually change the outcome.

A very minimal LLM agent loop with tools and skills

We check whether your agent has an alibi for what it did.

Shared artifact-creation harness for agentic workflows: renders docx/pptx/xlsx/pdf or delivers arbitrary files, with pluggable destinations and verified writes. Installs as agent-artifact-kit, imports as artifactkit.

Transparent, framework-agnostic assurance checks for AI agents, mapped to OWASP Agentic security standards.

Dependency-free tools for an AI agent that keeps records about itself: an append-only ledger verifier, a sandbox egress prober, and an approval-effect checker.

A real-time tool-call firewall for AI agents, built on TypeSafe's Jev.

Alpha recorder for signed JEP events, evidence digests and incident review

Local message bus between terminal coding agents: Claude Code, Codex, Muse, OpenCode, Pi, Cursor

Give your agent a filing cabinet.

Licensed local MCP server. Evaluate supplied AI capability offers against explicit cost, permission, license and data-handling policy before purchase.

Structured corpus of AGENTS.md — the written rules humans hand to AI agents ｜ 人写给 AI 智能体的书面规约的结构化语料库

Portable FastAPI and LangGraph chat with a bundled static UI

Deterministic command-line mocks for isolated agent skill testing

Durable, policy-aware orchestration primitives for multi-agent systems

One interface through which a coding agent spawns agents on any harness and exchanges messages with them

Agent Conformance Engine (ACE) - deterministic conformance evidence for AI agents. Placeholder release; see the repository for the specification and roadmap.

Python client for Wiggle (wiggle.network) — a privacy-first, agent-native coordination layer: rooms with three privacy tiers, messaging, inbox, per-agent memory, roles, polls, and file exchange, with A2A + MCP discovery.

Licensed local MCP server. Verify supplied agent delegation chains, effective scope, action permissions and spend facts before relying on retrospective evidence.

Framework-agnostic Python library for diagnosing LLM agent execution failures

Token-efficient Discogs CLI for AI agents

Runner SDK - Framework-agnostic agent runtime

Core protocols and models for Atlas Agent Engine

Google ADK adapter for Atlas Agent Engine

Atlas Agent Engine LangGraph SDK for building secure, observable agents.

Slim public Memory facade and models for Atlas Agent Engine

Evidence-preserving evaluation of complete agent systems

Generate guardrail evaluation plans, JSONL suites, and remediations from agent contracts

Deterministic benchmark harness for command-line coding agents

Conformance corpora and reference verifiers for agent evidence records

Self-improving agents through continual learning: in-process agentic RL that turns your own agent's work into training data. Observed tool outcomes, outbound-only, one runtime dependency.

Azure DocumentDB vector stores for Microsoft Agent Framework.

MongoDB vector stores for Microsoft Agent Framework.

A fast, lightweight harness for building production AI agents: agents, sub-agents, skills, prompts, tools, MCP, memory and the runtime rails underneath them.