Skip to content
Alternatives
Software like harnessgym
What else does this job. Matched on what each project does, not on who links to whom.
Closest first
- harness-arenapypi.orgharness-arena is an Apache-2.0 Python package for benchmarking agent harnesses against a single model using Terminal-Bench 2. It is intended for developers evaluating and comparing agent systems.
- 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.
- 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.
- 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.
- 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.
- Armature Harnessgithub.comHarness engineering framework for AI coding agents -- the invisible skeleton that shapes agent output
- 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.
- 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.
- harness-scorecardpypi.orgharness-scorecard is an open-source CLI tool that provides linting, A-F maturity grading, and security analysis for coding-agent harnesses such as Claude Code and Codex. It helps developers maintain high code quality and security standards.
- ctx-harnesspypi.orgctx-harness is a Python package for containing unbounded tool output in AI agent workflows. It stores output as immutable artifacts and emits bounded, deterministic digests for repository-aware agents such as Antigravity, with MCP-related support.
- everyharnesspypi.orgeveryharness is an offline-first command-line and terminal user interface for running locally available machine-learning models through pluggable harnesses. It is intended for developers and ML practitioners who need a flexible local model runner.
- harness-bench-fastpypi.orgharness-bench-fast provides a standardized, self-contained benchmark with 298 tasks covering file operations, code editing, CSV/SQLite/XLSX data pipelines, memory management, and other agentic scenarios. It is designed for rigorous evaluation of AI agents and frameworks such as LangChain. The package is open source under the MIT license and available on PyPI and GitHub.
- 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.
- superharnessgithub.comsuperharness is an open-source CLI framework for managing session handoff between multiple AI coding agents, such as Claude Code and Codex. It is designed for developers and researchers working with autonomous agent systems.
- 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.
- granary-harnesspypi.orggranary-harness is an open-source harness for agent security, governance, and privilege containment. It provides tools for enforcing zero-trust principles and managing agent permissions, making it suitable for developers building secure, autonomous agent systems.
- agentgauge-harnesspypi.orgagentgauge-harness provides a statistical regression testing framework specifically designed for MCP (Model Context Protocol) tool descriptions. It quantifies whether modifications to tool definitions result in measurable improvements or regressions in agent task success rates. It also includes a deterministic defect linter as a secondary utility. The package is intended for developers building and iterating on AI agents that use tool-calling interfaces.
- harness-observability-layergithub.comObservability tooling for agent harness sessions, imports, and reports.
- 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.
- spice-harnesspypi.orgspice-harness is an open-source CLI tool that provides an agent harness for coding repositories, enabling developers to automate, integrate, and control agent workflows in their codebases. It is designed for developers seeking to streamline agent-based automation and integration tasks.
Ranked by how close each one sits to harnessgym in the index, not by popularity. Back to harnessgym →