Skip to content
Alternatives
Software like superharness
What else does this job. Matched on what each project does, not on who links to whom.
Closest first
- pyagent-harnessgithub.comA lightweight agent harness built with Textual and a configurable multi-provider backend
- autoharnessgithub.comGlobally-installed agent harness framework that generates AI coding assistant primitives into any target workspace
- local-agent-harnessgithub.comlocal-agent-harness is an open-source CLI tool for managing the maturity and readiness of local AI coding agents such as Claude Code, Codex CLI, and Copilot CLI. It provides auditing, skill installation, and CI integration for developers working with AI agents.
- ai-harness-clipypi.orgai-harness-cli is an MIT-licensed command-line tool for installing tool-agnostic agents, skills, commands, hooks, and rules across AI development tools. It is intended for developers managing reusable AI tooling configurations across environments such as Claude Code, Codex, and OpenCode.
- harness-flowpypi.orgharness-flow is an open-source multi-agent development framework designed for building and reviewing AI agent workflows. It features a 5-role review process and integrates with Cursor, enabling developers to coordinate, test, and iterate on agent-based systems efficiently.
- harness-orchestratorgithub.comharness-orchestrator is an open-source framework for developing multi-agent systems, featuring a 5-role review process to streamline code review and collaboration. It is aimed at AI developers and researchers building agent-based applications.
- singleyunn-harnesspypi.orgsingleyunn-harness is an open-source Python agent harness for building and running safer, observable, extensible AI agent workflows. It is intended for developers integrating agent execution into Python projects.
- minimal-harnessgithub.comminimal-harness is an open-source, lightweight SDK for developers to build autonomous agents. It focuses on minimalism and effectiveness, providing CLI support and customization options for agent development.
- harness-agent-researchpypi.orgharness-agent-research is an open-source Python package that helps developers scaffold self-improving agent governance frameworks, including meta-skills, hooks, and memory hierarchies. It is designed for AI researchers and developers working with agent-based systems, particularly those integrating with Claude Code.
- agent-security-harnessgithub.comagent-security-harness is an open-source CLI tool that automates security and compliance testing for AI agent systems. It supports MCP and other protocols, providing a comprehensive suite of tests aligned with industry standards for developers and security teams.
- marim-harnesspypi.orgmarim-harness provides an embeddable coding-agent framework built on Pydantic AI. It offers both a Textual-based terminal user interface and a headless mode for automation and integration. The package is designed for developers who want to run, test, and embed LLM-powered coding agents in their own tools or workflows.
- harness-makergithub.comharness-maker is an open-source CLI tool that builds project-specific AI coding harnesses for code review, profiling, and automation. It integrates with Claude Code and other AI models to streamline development workflows for software engineers.
- Harness CLIrexai.topHarness CLI is a local workflow layer for AI coding clients including Codex, Claude, Gemini, OpenCode, Hermes, and Grok. It adds project memory, multi-agent collaboration, model routing, workflow governance, and verification without replacing the underlying coding client.
- Armature Harnessgithub.comHarness engineering framework for AI coding agents -- the invisible skeleton that shapes agent output
- team-harnessgithub.comteam-harness is an open-source CLI orchestration harness for coordinating multi-agent LLM workflows. It enables a coordinator LLM to spawn and manage external worker CLIs, supporting model-agnostic and complex agent-based systems.
- harnessieharnessie.comHarnessie is an open-source framework designed for verifiable orchestration of multi-agent AI workflows, emphasizing user control and auditability. It addresses the risks of unsupervised AI by ensuring that every action taken by an AI model is subject to independent verification and explicit user consent before any side effect occurs, such as changing a file or running a command. No sensitive data leaves the models controlled by the user, and every action—whether by AI or human operator—is recorded in a hash-chained audit log, making tampering detectable. The framework structures jobs using three types of agents: an orchestrator that decomposes tasks, workers that execute tasks in isolated environments, and verifiers that independently check results. Each step in a workflow is separated by checkpoints, and the system defaults to failing closed, meaning no action is completed without explicit approval. When a judgment call is required, the process halts for human intervention, ensuring the final decision remains with the operator. Disagreements between agents are recorded rather than averaged, and declined actions are logged without being overridden. Harnessie is brain-agnostic, allowing users to switch between local, private, or remote AI models—including those accessible via OpenAI-compatible endpoints—by editing a single configuration file. The framework supports eight providers and eleven verified models, and its structure remains consistent regardless of the underlying model. Installation requires Python 3.11+ and PyYAML, and can be performed using pip, pipx, uv, or brew. Model adapters rely on the standard library, with no dependency on vendor-specific SDKs. The tool is self-hostable and released under the Apache-2.0 license. It includes a test suite and evaluation scorecard that can be run against a deterministic mock environment without network access, allowing users to validate its operation before integrating any API keys. Harnessie is suited for developers and operators who need strict control, verifiability, and auditability in multi-agent AI workflows, particularly where sensitive data and independent verification are priorities.
- hiclaw-harness-workerpypi.orghiclaw-harness-worker is an open-source CLI tool that delegates agent loops to various AI code models, including Claude Code, Gemini CLI, OpenCode, and Codex. It includes a remote harness CLI for developers automating agent workflows.
- OpenHarnessopen-harness.devOpenHarness is an open-source toolkit designed for building AI agents in code, offering developers composable and stateless primitives to create agent harnesses similar to Claude Code-like products. It provides a TypeScript SDK that enables full control over agent behavior, message history, and state management, allowing users to inspect, modify, or share state between agents as plain arrays. The platform is built on top of the Vercel AI SDK, supporting integration with model providers such as OpenAI, Anthropic, Google, or any compatible provider. Key features of OpenHarness include composable middleware for functionalities like turn tracking, retries, context compaction, and persistence, which can be mixed and matched as needed. Developers can implement subagent hierarchies, delegating tasks to specialized child agents with background execution and Promise-like combinators. The toolkit also supports automatic two-phase context management, which involves pruning old tool results and applying LLM-powered summarization to maintain relevant context for the agents. Tool permissions can be managed through asynchronous approval callbacks, enabling gating of tool execution in various interfaces including CLI prompts, web modals, or external services. OpenHarness also offers integration with the Model Context Protocol (MCP), allowing connection to any MCP server via standard input/output, HTTP, or SSE transport. md files. The SDK is compatible with both web and CLI environments, providing React hooks, Vue composables, and streaming support to build agents for any runtime. js or edge runtimes. OpenHarness is released under the MIT License and developed by MaxGfeller, emphasizing its open-source nature and flexibility for developers seeking to construct advanced, customizable AI agent systems.
- Liu-Agentgithub.comLiu-Agent is an open-source, autonomous code-writing agent built on the Harness architecture. It leverages large language models to automate coding tasks and is accessible via the command line, targeting developers and AI researchers seeking automation in software development.
- screen-harnessgithub.comCLI-first screen recording and SOP rendering harness for AI agents.
- godharnesspypi.orggodharness is an open-source Python framework for managing agent context and documentation governance. It provides developers with tooling to structure, maintain, and govern documentation used by software agents.
- harnessgympypi.orgharnessgym is an open-source CLI framework for benchmarking, testing, and improving agent harnesses for AI code agents such as Codex. It supports iterative improvement, MCP, and is designed for AI researchers and developers.
- harness-to-mcpgithub.comTurn harness internal tools into a standard MCP server — compatible with Claude Code, Codex, OpenCode, and more.
- agent-session-hubpypi.orgagent-session-hub provides local-first tooling to discover, export, and create baselines from multi-agent AI coding sessions. It supports popular models including Claude, Codex, Copilot, DeepSeek, Gemini, and Grok. Designed for developers working with agentic coding workflows, it enables better session management and reproducibility under an MIT license.
- subagent-harness-mcppypi.orgSubagent Harness MCP is an open-source MCP gateway that lets Codex orchestrate external coding agents through their native harnesses. It is intended for developers building multi-agent coding workflows involving tools such as Claude Code and other coding agents.
- oneharness-clipypi.orgoneharness-cli is an open-source command-line tool that enables developers to run multiple agentic coding harnesses non-interactively and receive standardized JSON outputs. It simplifies the orchestration of agent-based coding workflows and is distributed under the MIT license.
- warrantor-harnesspypi.orgwarrantor-harness is an Apache-2.0 Python package that wraps coding agent harnesses such as Claude Code, Codex, and Cursor with AumOS security capabilities. It is intended for developers building or operating secure AI-assisted coding workflows.
- harness-observability-layergithub.comObservability tooling for agent harness sessions, imports, and reports.
- deepseek-harnessx-cmd.comdeepseek-harness is an open-source agent harness for developers building configurable AI agents. It provides swappable plugins for models, tools, sessions, sandboxes, storage, scheduling, and UI, with a locally launchable browser interface.
- harness-babypypi.orgHarness Baby is an MIT-licensed command-line tool that bootstraps and scores repository harnesses for coding agents. It is intended for developers who need to configure and evaluate repository-level tooling using static analysis.
- handoff-agentgithub.comSeamlessly switch between AI coding agents without losing context.
- sage-harnesspypi.orgsage-harness is an open-source CLI tool that offers governance and closed-loop specification workflows for AI coding agents such as Claude Code and Codex. It integrates spec-SSOT and automation hooks, targeting AI developers building or managing agent-based coding systems.
Ranked by how close each one sits to superharness in the index, not by popularity. Back to superharness →