revfactory/harness
A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.
Language: HTML
#claude_code #claude_code_plugin #harness #harness_engineering
Stars: 582 Issues: 0 Forks: 76
https://github.com/revfactory/harness

stanford-iris-lab/meta-harness
Reference code for the Meta-Harness paper.
Language: Python
#harness_engineering #llm_agents
Stars: 540 Issues: 1 Forks: 42
https://github.com/stanford-iris-lab/meta-harness

chaitanyagiri/munder-difflin
local multi-agent harness
Language: TypeScript
#agents #claude_code #free #harness #harness_engineering #memory
Stars: 420 Issues: 23 Forks: 43
https://github.com/chaitanyagiri/munder-difflin

fivetaku/fablize
A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.
Language: Shell
#agentic #anthropic #claude #claude_code #fable #harness #opus
Stars: 372 Issues: 0 Forks: 66
https://github.com/fivetaku/fablize

vercel/eve
The Framework for Building Agents
Language: TypeScript
#agent #framework #harness #javascript #markdown #sandbox #typescript #vercel #workflows
Stars: 923 Issues: 21 Forks: 41
https://github.com/vercel/eve

modiqo/waggle
Attributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world.
Language: Rust
#ai_agents #harness_engineering #llm_tools #loop_engineering
Stars: 692 Issues: 0 Forks: 138
https://github.com/modiqo/waggle

AMAP-ML/LongHorizon-Harness
The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.
Language: Python
#agent #claude #claude_code #claude_plugin #cli #codex #codex_desktop #codex_plugin #cua #gui #harness #long_horizon #long_horizon_agents #longhorizon_harness #loop #loop_engineering
Stars: 524 Issues: 6 Forks: 64
https://github.com/AMAP-ML/LongHorizon-Harness

0xsline/awesome-deepseek-harness
DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic.
Language: Python
#agent #ai #ai_agents #ai_tools #awesome #awesome_list #coding_assistant #curated_list #deepseek #deepseek_harness #developer_tools #dsh #dsh_plugin #dsh_plugins #harness #llm #mcp #plugins
Stars: 527 Issues: 0 Forks: 190
https://github.com/0xsline/awesome-deepseek-harness

ApodexAI/FrontierAgent
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
Language: Python
#agent_orchestration #agentic_ai #agentic_framework #ai_agents #harness #multi_agent #terminal_agent #tui
Stars: 738 Issues: 0 Forks: 66
https://github.com/ApodexAI/FrontierAgent

ZiChuanLan/agent-purge
One persona, many coding agents. Replace or inject system prompts across codex, claude, opencode, grok, omp, hermes, pi, zcode - with a local web console.
Language: JavaScript
#claude_code #codex #coding_agent #deepseek_harness #harness #omp #opencode #pi #system_prompt
Stars: 835 Issues: 1 Forks: 622
https://github.com/ZiChuanLan/agent-purge