Build stateful agents with memory, identity, and long-term learning
Project overview
Letta Code is a stateful agent harness built around persistent memory, identity, and experience over time. Agents can revise their own memory, skills, and prompts as they learn, while remaining accessible through a CLI, desktop app, browser, or messaging channels. Message search, subagents, and schedules support work that continues across sessions.
Run and switch between coding agents from one terminal UI
Project overview
Toad combines a traditional shell with a terminal UI for working with coding agents such as Claude, Gemini, and Codex. Its agent catalog lets you find, install, and run compatible tools from one interface, while Agent Client Protocol support gives developers a way to add more agents.
Plans and runs multiple coding agents in isolated local or remote workspaces.
Project overview
Mux is a desktop and browser application for planning, running, and comparing work from multiple AI agents. A workspace can use the local project directory, a local Git worktree, or a remote server over SSH, while the app supports several cloud models, Ollama, OpenRouter, and a VS Code extension. Prebuilt releases target macOS and Linux.
Agent harnessCommunication and collaborationClaude Code
talon
@dylanneve1·TypeScript
Run one self-hosted AI agent across chat platforms, terminals, and companion apps.
Project overview
Deploy the same agent through Telegram, Discord, Microsoft Teams, a terminal, or desktop and mobile companion clients. Talon supports interchangeable Claude, Codex, Kilo, OpenCode, and OpenAI Agents backends, along with MCP tools, hot-reloadable plugins, persistent goals, and scheduled background agents. Source installation requires Node.js 24 or later, while releases also provide standalone binaries for several platforms.
Manage many coding-agent sessions from one terminal interface
Project overview
Agent Deck provides one terminal view for coding-agent sessions across many projects, making it easy to see which are running, waiting for input, or finished. Groups, search, session forking, and Git worktrees help organize parallel work, while the conductor can surface sessions that need attention remotely.
A coding-agent kanban and isolated-workspace tool that has announced it is sunsetting.
Project overview
Vibe Kanban has announced that it is sunsetting. Its existing workflow organizes work as prioritized kanban issues and creates agent workspaces with a branch, terminal, and development server. The interface supports diff review, inline comments, application previews, and switching among coding agents such as Claude Code, Codex, and Gemini CLI.
Route coding-agent work through replayable, evidence-gated multi-agent lanes
Project overview
OMK is a provider-neutral control plane for Codex, Claude Code, OpenCode, and local coding agents. It routes work into scoped DAG lanes, verifies and measures execution, exposes MCP and context-budget state, and records artifacts that can be replayed; the monorepo also ships an interactive CLI, agent runtime, multi-provider LLM API, and operator TUI. OMK extensions and MCP servers support workflow integrations such as Slack or chat automation.
Agent harnessAI and agent developmentModel Context Protocol
dexto
@truffle-ai·TypeScript
Configure and run stateful agent applications with tools, memory, and multiple interfaces.
Project overview
Dexto is an agent harness for defining models, tools, and behavior in YAML rather than wiring every workflow by hand. It includes sessions, persistent memory, tool orchestration, multimodal input, and observability, with a ready-made coding agent as an example. Agents can run locally, in the cloud, or through CLI, web, REST, Discord, and Telegram interfaces.
Build and run open agents with tools, memory, permissions, and multi-agent coordination.
Project overview
OpenHarness is a Python framework for researchers and developers who want an inspectable, extensible agent runtime through a CLI or terminal UI. It combines tool use, skills, persistent memory, permissions, MCP, and multi-agent coordination. The bundled ohmo agent can work through Feishu, Slack, Telegram, or Discord using an existing Claude Code or Codex subscription.
Let an AI agent work across code, websites, and office files on a Linux desktop.
Project overview
Agent Zero runs an agent inside a Dockerized Linux desktop, where it can use terminals, browsers, desktop software, repositories, and editable documents, spreadsheets, and presentations. Projects isolate files, memories, secrets, and model settings, while multi-agent delegation, MCP, a host-machine bridge, and more than 100 community plugins extend the workspace. When connecting it to real host repositories, carefully limit the paths and permissions it can reach.
Scaffold a test-first harness for AI agents in any repo
Project overview
Claude Harness scaffolds a repository-level working framework for AI-agent work. It creates concise rules, active and completed execution plans, lessons, and a technical-debt tracker, then uses failing tests to lock behavior before implementation. Review, phase-finish, and lesson-promotion steps keep the context current over longer projects, making it useful for new codebases, refactors, and durable maintenance.
Run a multi-provider coding agent from one lightweight Go binary.
Project overview
zot packages a coding-agent loop into a single Go binary with interactive TUI, print, and JSON modes plus read, write, edit, and shell tools. It supports many direct APIs, selected subscription logins, cloud platforms, and local Ollama-style models, with session recovery and cost tracking. Optional subprocess extensions can be written in any language, and a built-in Telegram bridge enables remote conversations.
Run coding agents through an independent verification loop
Project overview
Zeroshot orchestrates an agent you already use through an executor-verifier loop. One agent writes the change, while an independent verifier checks the result without seeing how it was produced and can request another pass. It supports Claude Code, OpenAI Codex, Gemini CLI, and OpenCode from a command-line workflow.
Build code from a specification with evidence-backed verification
Project overview
Loki Mode turns a PRD, issue, API specification, or short brief into a repository with source, tests, configuration, and audit records. Its agents repeat reason-act-reflect-verify cycles, while deterministic gates block empty diffs, failing tests, and inconclusive checks from being reported as complete. Each run can produce evidence that the completion claim can be rechecked.
Combines AI coding CLIs into reusable, parallel, and long-running workflows.
Project overview
CodeMachine is an orchestration layer for AI coding CLIs such as Claude Code, Codex, and Cursor. Define a workflow once and it handles step execution, context passing, and agent coordination. Workflows can range from interactive to fully autonomous, divide work among multiple agents, run tasks in parallel, and persist for hours or days. The underlying coding CLIs must be available separately.
Write self-healing web and mobile QA tests in natural language
Project overview
agent-qa lets teams describe web and mobile tests in natural language, then re-observes the interface and tries another path when an action drifts or fails. It learns from previous runs, exposes a CLI and dashboard, supports MCP and multiple model providers, and can run setup or teardown hooks inside Docker containers. Docker is required for those hooks, and the harness remains an aid to a team's own release checks.
Build composable AI agents with tools, sessions, middleware, and subagents.
Project overview
Create general-purpose agents in TypeScript with streamed events, filesystem or shell tools, persistent multi-turn sessions, and middleware for compaction, retry, and turn tracking. The SDK also covers subagents, MCP servers, on-demand skills, virtual filesystems, and React or Vue chat integration on top of Vercel's AI SDK.
Run long coding tasks through an editable local agent harness with readable traces.
Project overview
Agent AFK provides an Apache-licensed harness whose prompts, gates, routing, skills, traces, and provider settings are editable. It supports terminal chat, headless background runs, Telegram notifications, orchestration commands, and migration of plugins or MCP servers from Claude Code or Codex. Node 22 is required, and optional remote notifications need their own credentials.