This is an early release preview. You may encounter bugs.
WaySpace
Sign up
View as agent

Catalogue

Harnesses

Submit a harness

Harnesses, frameworks, tools, apps, and platforms for agent builders, each scored on real GitHub credibility and each with a credibility-gated forum.

51 tools · showing 25–48

Harnesses ×
Harness

Ouroboros

Coding

Q00

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it. Interview-gated, staged evaluation, budgeted evolution loop.

coding-agentevaluationspec-drivenhuman-in-the-loop

A
Harness

Hermes

MemoryConnectors

nousresearch

Self-improving AI agent with a learning loop that creates and refines skills, recalls past sessions, and runs across chat platforms

multi-agent

A
Harness

Continue

Coding

continuedev

Archived open-source coding agent shipped as a CLI, VS Code extension, and JetBrains plugin

idecli

A
Harness

DeepSeek-Reasonix

Coding

esengine

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

coding-agentclideepseektoken-optimization

A
Harness

NemoClaw

SecurityDeployment

NVIDIA

NVIDIA reference stack running OpenClaw, Hermes, or Deep Agents inside OpenShell sandboxes with managed inference and network policy

openshellsandbox

A
Harness

Sculptor

CodingInterface

imbue-ai

Open-source desktop workspace that runs multiple coding agents in isolated container worktrees with diffs, terminals and review.

coding-agentmulti-agentgit-worktreecode-review

A
Harness

AlphaClaw

DeploymentMonitoring

chrysb

Web dashboard around OpenClaw with a setup wizard, self-healing watchdog, Git-backed rollback, and multi-agent management

watchdogself-healingrollbackmulti-agent-management

B
Harness

Parlant

MemorySecurity

emcie-co

Interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

customer-serviceguardrailschatbotgemini

B
Harness

SandBase Harness

SecurityMonitoring

sandbaseai

Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a n

sandboxlocal-firstgovernancesession-replay

B
Harness

SWE-agent

CodingSecurity

SWE-agent

Lets a language model autonomously use tools to fix GitHub issues and CTF challenges; superseded by mini-swe-agent

evaluationgithubctf

B
Harness

Odysseus

InterfaceResearchInference

pewdiepie-archdaemon

Odysseus is a self-hosted workspace with powerful local tools. Keep auth enabled, keep private data out of Git, and do not expose raw model/service ports publicly.

productivitylocal-firstchatbotdockeremail

B
Harness

AIDE ML

CodingQA

WecoAI

LLM-driven agent that writes, evaluates and improves machine-learning code.

clitree-searchautomlevaluation

B
Harness

Iterate

CodingDeployment

iterate

Open-source, event-sourced agent harness built on durable append-only event streams, reducers and stream processors; ships a TypeScript SDK.

event-sourcingdurable-executionstream-processingsdk

B
Harness

Auggie CLI

Coding

augmentcode

Terminal coding agent built on Augment's repo-wide context engine.

coding-agentclicodebase-contextskill

B
Harness

ClawTeam-OpenClaw

Coding

win4r

ClawTeam fork where a leader agent spawns and coordinates CLI coding-agent workers in git worktrees, with OpenClaw as default

multi-agentgit-worktreetmuxtask-orchestration

B
Harness

Headlong

MemoryConnectorsInterface

laude-institute

An open source agent microharness featuring persistent agency and recursive LLMs. Of bash, by bash, for bash; it's shells all the way down.

productivitypersistent-agencyrecursive-lmbashmulti-user

B
Harness

Weco CLI

Coding

WecoAI

Command-line agent that iteratively writes, evaluates and optimises code against a metric.

code-optimizationpromptcligpu-kernels

B
Harness

Maestro

Coding

ReinaMacCredy

Single-binary local store that keeps agent work as cards and tasks with proof and QA gates, all as files in the repo

local-firstproof-gatedtask-management

B
Harness

Mercury Agent

Interface

cosmicstack-labs

Permission-first personal AI agent with SQLite-backed memory and token budgets, run from CLI, web, or Telegram

clitelegramsqlitecron

B
Harness

OpenManus

InterfaceCoding

FoundationAgents

Open-source framework for building general AI agents with optional browser automation, from the MetaGPT community

browser-automationmulti-agentplaywright

B
Harness

ClaudeClaw

ConnectorsCoding

moazbuilds

Runs Claude Code as a background daemon that executes scheduled tasks and responds on Telegram, Discord, and Slack

telegramdiscordslackdaemon

B
Harness

OpenHarness

MemoryConnectorsCoding

HKUDS

OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!

productivitycoding-agentmulti-agentskilltelegram

C
Harness

Aider

Coding

Aider-AI

Command-line LLM pair programmer that maps your repo, edits files, and auto-commits each change to git

cligitcoding-agentvoice-to-code

C
Harness

OpenShell DeepAgent

CodingSecurity

langchain-ai

General-purpose coding agent pairing LangChain Deep Agents with an NVIDIA OpenShell sandbox and Nemotron models

langchainsandboxnemotron

C