Python agents

Reserva de nome. O pacote real e privado, da Starbem — este nao tem funcionalidade.

Agentic, safety-first storage analysis and optimization TUI built with Textual and Pi

GitHub-repository Storage backend for Strands Agents — persists keys as versioned, diffable files in a repo.

MongoDB implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory

SQL (SQLAlchemy) implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory

Amazon DynamoDB implementation of the Strands Agents Storage interface — durable bytes-under-keys for sessions, context offload, and memory

Canonical delegation contract schema + enforcement hooks for parent->subagent fidelity in AI coding workflows.

Production-ready, lightweight Hybrid RAG (Dynamic Vector + Full-Text Search + Facets) engine for Supabase.

Framework-agnostic AI/LangChain engine: OpenAI/Anthropic/Bedrock chat models, Pydantic structured outputs, tool-calling agents, and pure cost calculators.

A local coding and terminal AI agent powered by an OpenAI-compatible Llama server.

A code agent built from scratch, no frameworks

Python SDK that enables developers to build and deploy Claude Agent SDK agents to the UiPath Cloud Platform

Slack-native approval queue for AI agents

Monitor, debug, and optimize your AI agents. Track LLM calls, costs, latency, and tool usage in real-time.

Thin client for buying work from Virohana over x402: discover the catalog, parse the 402 quote, verify the receipt offline.

Speechify TTS integration for Vision Agents

Bring the brain, we bring the voice: write a plain Python Brain, Voqalize runs the voice.

MCP agent framework for Viveka Sutra — build FastMCP-powered agents with tools, resources, and prompts

Enterprise RAG framework with pluggable layers

Signed, tamper-evident receipts for A2A and MCP agent interactions (triple-entry accounting)

Ceph S3 storage plugin (croit and RadosGW flavours)

AumOS Agent SDK — unified Python SDK that gives coding agents AumOS security primitives as first-class objects

The OpenAI Agents SDK (Python) adapter for Welt's wire contract

Framework-agnostic SDK for building A2A/kagent-compliant agent runners.

Lightning Bitcoin payments for autonomous AI Agents.

A policy enforcement point for agent spending: blocks transactions that violate a declarative policy and writes a tamper-evident, signed audit log of every decision.

Python SDK for Agent Browser Knowledge Graph API - The Google for AI Agents

PostgreSQL Copy-On-Write for AI agent workspace isolation

Event-sourced experience capture, validation, and reuse for AI agents.

Agent control surface: vault-backed rollback, typed hooks, circuit breaker, audit log

Execution integrity and trajectory authenticity governance middleware for autonomous AI agents

One-liner audit trails + policy enforcement for LangChain, LlamaIndex and OpenAI Agents — zero dependencies

Agent Push Kit API

Agent Security Evaluation Kit — score agent code and refuse unsafe tools, with receipts, AST checks, and live-trace adapters.

Git-backed registry and guardrails for shared agent skills.

Deterministic policy engine for LLM-generated SQL: SELECT-only, PII column denylist, table allowlist, cost cap. Multi-dialect via sqlglot (BigQuery, Snowflake, Postgres, Trino, …).

Durable Agents for Agent Swarms, LLMs, and Autonomous Systems

Project typed Python operations as agent-friendly CLIs, MCP tools, and schemas

A developer-first package to evaluate and find regressions in agent trajectories

Control coding agents from chat, with a permission floor the trust toggle cannot reach

Agent fleet management tool

Local-first analytics for AI coding agents. Reads the session logs already on your disk.

Transaction-safe policy, approval, and execution gateway for AI-agent actions

Bridge OpenAI tools to Claude Code SDK, Codex CLI, and OpenRouter

Reserved alias of the Chock project -- install 'chock' instead

Multi-agent synthetic arbitration and escrow protocol client for autonomous AI commerce.

Coordinator that runs a small graph of AI-agent nodes with bounded spend, mechanical gates and journaled state

Universal AI Agent Factory: SDK + self-hosted Studio for building and operating any AI agent

Firewall for AI coding agents. Intercepts Bash/Read/Write/Edit, blocks outbound HTTP, asks humans via Slack/Telegram for risky ops. Works with Claude Code, Cursor, Continue.dev, Aider, and GitHub Actions.

AgentGov CLI — wrap Claude Code, bind work items, check gateway health.

AgentGov FastAPI gateway (vaults ANTHROPIC_API_KEY; enforces from signed policy cache; §12.1)

Executable architecture governance for autonomous coding agents

The Engineering Operating System for AI Coding Agents

Structured logging for Coding Agents - write once, read efficiently

Provider-neutral skills and deterministic tooling for bounded agent engineering: context bundles, evidence, environment snapshots, hotspot analysis, and footprint records.

Govern AI-assisted repository work with explicit contracts, gates, evidence, and handoffs.

Open-source defensive harness and learning lab for reproducing and measuring agentic AI failure modes with portable traces, attack graphs, scorecards, and data-boundary tests.

An MCP server that gives an agent terminal capabilities: run shell commands, run Python, and manage files.

An MCP which adds terminal capabilities to an agent

An MCP which adds terminal capabilities to an agent.

Unified control plane and operations console for the DeepAgentLabs ecosystem.

Generate AGENTS.md from a repo's actual config — evidence-based, no guessing.

Textual TUI front-end for agentknit coding agents.

Find out why your coding agent is expensive — offline waste detection, loop detection and skill generation across 7 coding agents.

Model-free tree-sitter repo-map, localization and patch-validation machinery for agents

Local-first verified coding workflow with optional GitHub and GitLab publication

Python client for Agent Media Tools — image processing, PDF tools, pastebin, webhooks, QR codes, and more

Self-improving loop for your existing AI agent: write GOALS.md, agentopt measures the gap and closes it - prompts, params, tools, workflow. No model training. Under active development.

AgentPerimeter — runtime governance for AI agents with CIS-region compliance (FSTEC 117, GOST R 57580, KZ AI Law). Name reservation; product at agentperimeter.ru

The AgentPlane control plane: stores Chronicle traces and serves TokenOps governance over HTTP.

Cryptographically signed, tamper-evident audit logs for autonomous agents

k-run wrapper for the EnterpriseOps-Gym benchmark: drives evaluate.py k times per task, archiving per-run DB state exports plus a batch manifest.

Provider-free Runner regression probes for the OpenAI Agents SDK

Build TRACE Trust Records from evidence another system produced, without fabricating what is not there

Explain which AGENTS.md instructions Codex discovers for any path

Local markdown memory & cross-agent context engine for coding agents (MCP).

Adapters from common agent instruction formats to Agent Skills (https://agentskills.io)

Query-time skill selection for the Agent Skills format (https://agentskills.io)

Conformance suite and test doubles for Agent Skills providers (https://agentskills.io)

Command line tools for authoring and validating Agent Skills (https://agentskills.io)

Declarative multiparty session protocols for AI agents

Python-first UI layer for LangChain and LangGraph agents

DEPRECATED — agentstow is now agent-sync: install agent-sync-sh instead

Agnos Proxy - the gateway-agnostic control plane for LLM routing, cost-tracking and observability. OpenAI-compatible governance proxy over a swappable BackendEngine.

A tool-agnostic policy layer that intercepts and blocks destructive commands proposed by autonomous AI coding agents, with full audit logging.

AIR (airanks) ACP agent — an Agent Connect Protocol server exposing AI optimization rankings (AIR score, tracked stats, AI-file posture, search) for any domain, callable from any ACP hub or catalog. Same auth as every AIR client. https://airanks.net

Governed Bedrock invocation — pre-check, invoke, evidence, record, trace (AIGP-aligned)

Local multi-agent coding orchestrator with a sandboxed git staging area and a human review gate

Areev storage backend for CrewAI memory: supersession-based updates, audited deletes, and right-to-erasure over memory sources

Areev persistence for LangGraph: a BaseStore and a BaseCheckpointSaver over content-addressed, governable memory files

Partner SDK for AI Agent Gateway realtime and call-history APIs

Agent-friendly Markdown-to-video automation pipeline with reproducible rendering and pluggable media providers.

An extensible terminal AI agent for research, knowledge retrieval, and software development.

Universal multi-host installer + MCP server for blind multi-model councils. Each council seat is a real agent CLI subprocess (claude/pi/codex). Ships to Claude Code, pi, Cursor, Codex, Copilot, Gemini. SQLite default, Postgres optional. BYO gateway.

An autonomous agent for indexing Python repositories and repairing reported bugs.

Cairn reuses unchanged RAG chunks with content-defined identities, cache-aware planning, and transactional indexing.

Official Python SDK for the CANDY AI Marketplace - deploy an AI business in 3 lines of code.

Typed, async Python SDK for AWS Bedrock Runtime.

CHAP bridge for LangGraph: emit hash-linked audit envelopes around human-in-the-loop interrupts.

CHAP adapter for LlamaIndex Workflows: record a human-decision envelope when a step pauses for human input.