Code agents

Versatile Python library designed for evaluating the performance of large language models in Natural Language Processing (NLP) tasks. Developed by Sagacify

Python-first Coding Agent API and CLI.

casual utility library for coding QoL

SAM — Smart Agentic Model: CLI coding agent for open-source LLMs

Run LLM agents inside disposable Docker sandboxes.

Python client SDK for Sandbox Agent — universal API for automatic coding agents in sandboxes

AutoGen code executor for Sandflare Firecracker microVM sandboxes — run agent-generated code safely

CrewAI tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely

LangChain tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely

LlamaIndex tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely

Product-agnostic build tooling for agent plugin packages.

GPT for satellite mission planning. In development. Get your API keys ready!

Python SDK for running coding agents in sandbox backends

AI Dependency Intelligence — scan, govern, and visualize AI in your code.

Autonomous, DSL-fluent coding agent built on the Claude Agent SDK — point it at any DSL directory and it plans, codes, debugs, verifies, and self-extends.

Declarative YAML-based framework for defining, managing, and orchestrating AI coding agent instances

Opinionated Claude Code wrapper: dangerous perms + non-destructive guardrails + auto Haiku handoffs instead of compacting.

Role-based, scoped AI query/edit operations for any codebase.

Installer for the cmdop CLI — stand up an AI agent on a machine you already have

Computer Use SDK for Python — build screen-controlling AI agents in a few lines of code

Tricentis Sealights Python Agent - Quality Intelligence and Code Coverage

Search across Claude Code session history

Trace storage format based on HDF5 developped by CEA

Deterministic security gate + bounded AI remediation prompt generator. NIST SSDF / OWASP ASVS / CWE Top 25 anchored.

Secure File Storage is a secure, encrypted file storage solution developed in Python. It combines strong encryption, modular architecture, logging and basic access control.

Local-first DLP engine and security layer for AI coding agents. Secures Copilot, Claude Code, Cursor, Windsurf, and any MCP-compatible agent.

A programming framework for agentic AI

A programming framework for agentic AI

Install seekdb Agent Skills to various AI coding tools (Claude Code, GitHub Copilot, Codex, Cursor, etc.)

Automatic repair for failing Python code, powered by any LLM.

Sentarc coding agent CLI (arc command)

A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent

Universal production server monitoring, healing, and reporting skill for cmdop

The official Python library for the sgptcoder API

CrewAI integration for SHIP Protocol - AI code reliability tools for multi-agent workflows

LangChain integration for SHIP Protocol - AI coding reliability metrics

Codegen Shopify agents in Ruby

A small example package

MCP server that gives AI tools Partner API access: MRR, churn, retention cohorts, merchant health, and 20+ computed analytics for Shopify app developers.

Sidekick Python Debugger

Open-core orchestrator logic for the Siglume API Store agent runtime — tool-manual quality scoring + LLM provider tool adapters + installed-tool prefilter + keyword-based tool selector + capability-failure learning helpers + orchestrate system-prompt / provider-tool / cost-estimation helpers + orchestrate inner loop with dispatcher callback bag + publisher dev-simulator pure helpers.

YAML-driven workflow engine for AI agents

Pre-built coding agents for AI-assisted software development

Manage Claude Code skills across projects

Personal collection manager for Claude Code artifacts (Skills, Commands, Agents, MCP, Hooks)

Active Skill Listener & Trainer — structured memory layer for AI coding assistants

Slack app for running Claude Code CLI commands

Slack CLI for coding agents — search, read, and draft messages via the Slack Web API using browser-extracted tokens

A lightweight and developer-friendly library for building and orchestrating AI agents

A library to identify devices (phones, tablets) and their capabilities by parsing browser user agent strings.

Code generation LLM agent for fast prototyping

Code generation LLM agent for fast prototyping

🤗 smolagents: a barebones library for agents. Agents write python code to call tools or orchestrate other agents.

Capsule sandbox integration for smolagents — run code in isolated WebAssembly sandboxes

smolagents tools for The Colony (thecolony.cc) — give any HuggingFace agent the ability to search, read, write, and interact on the AI agent internet

smolagents Tool subclasses for the Ejentum Reasoning Harness. Eight tools: four dynamic (reasoning, code, anti-deception, memory) and four adaptive (adaptive-reasoning, adaptive-code, adaptive-anti-deception, adaptive-memory) that pre-fit the operation to the task via an adapter LLM. Each call returns a structured cognitive injection: a natural-language procedure plus an executable reasoning topology.

A tool to create readable snapshots of your codebase

Run Claude Code against Claude models hosted on Snowflake Cortex.

AI-powered FHE smart contract generator for Fhenix CoFHE

Simple coding agent.

Space: A powerful, fully local CLI coding assistant powered by Ollama.

YAML-driven workflow engine for AI agents

Pre-built coding agents for AI-assisted software development

LLM assistant for the development of Spark applications

Auto-generate an Obsidian knowledge wiki from every git push, powered by Claude

Hardware specification analyzer for embedded software development -- datasheets, register maps, protocols, constraints

Spec-driven workflow system for autonomous AI-assisted software development

LLM application development framework

Python tool designed to reorganize large Python projects into minified files based on a specified token limit. This is particularly useful for processing large Python projects with GPT models, as it allows the models to handle the data in manageable chunks.

Turn any AI agent into an agile developer. Persistent sprint context for Claude Code, Cursor, Copilot, Codex, Gemini, Aider, Windsurf. Zero dependencies.

Spyder plugin for Claude Code interaction

Dead-simple, local-first, framework-agnostic agent observability. One decorator, one SQLite file, full tracing.

A wrapper for ssh-add that checks whether a key has already been added to the SSH agent rather than prompting for the passphrase every time.

Agent framework that builds evidence chains from Crash/ANR/OOM logs, auto-fixes Crash code, and plugs into test verification & bug trackers

StableOpenai is an enhanced framework for OpenAI, providing stable and efficient API request management. It allows the use of multiple API keys to increase request limits and ensures thread safety. The library features multi-key management, thread-safe operations for reliable requests in multi-threaded environments, and automatic fallback to alternate keys when API rate limits are reached. Ideal for developers looking to optimize interactions with OpenAI's services in robust, concurrent applications.

AI-assisted software development with a sci-fi inspired interface

CLI-native Stata integration for AI agents. Run code, inspect data, retrieve results, export graphs, and test do-files.

Claude Code plugins for autonomous development workflows

Easy to work with Google Cloud Platform Storage Bucket wrapper

Helpful context managers for managing decryption and mounts of storage devices

Python bindings for storage-layout-extractor - EVM bytecode storage layout analysis

Secure server management agent for Storm Developments infrastructure

A model-driven approach to building AI agents in just a few lines of code

A coding agent built on Strands Agents SDK that uses code generation as the primary action interface

An API framework for simplified development

CLI tool to strip ChatGPT-specific markers from text

Deterministic mock server for LLM APIs. Test your AI code without spending tokens.

Route LLM API calls through subscription-authenticated coding agents (Claude Code, Codex, Gemini CLI)

Claude Code session log explorer

Bridge Claude Code sessions to Slack channels

Compile a single AI supagent into multiple AI subagents.

SuperSearch is a powerful Python package for advanced search and data extraction. It leverages the GPT-4 AI model, Google search, and web scraping to efficiently obtain information on various topics. Ideal for developers needing quick, accurate responses to complex queries and data extraction, analysis, and summarization from multiple web sources. Easy to integrate, SuperSearch enhances functionality and user experience, saving time on manual research and enabling smarter, more effective solutions.

Unofficial implementation of the Meta Harness paper for coding-agent harness optimization.

superagi-tools is a python library specifically designed for developers working with SuperAGI. The library offers the BaseToolkit and BaseTool classes, requierd for development of custom tools and toolkits for SuperAGI.

AI-enhanced development framework for Claude Code - pytest plugin with optional skills

DEPRECATED — renamed to claude-primer. Install with: pip install claude-primer

Superset multi-environment workflow manager using git worktrees

An agent for monitoring applications run by supervisor

GPU-first RAG engine with cross-encoder reranking and quality validation. One engine, any domain.

An agentic framework that does exactly one thing: software development.