Skip to content
OpenAPPA

Self-hosted alternatives to OpenAPPA

200 self-hosted apps like OpenAPPA, closest match first.

Top picks

  1. A

    Adrian

    Launch

    Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

    Self-hosted

  2. O

    Opengeni

    Launch

    Open, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.

    Self-hosted

  3. O

    OpenTaint

    Launch

    The open source taint analysis engine for the AI era. A formal dataflow analysis tool you can customize and self-host, built so AI agents drive your application security analysis without burning tokens on every scan. AI-ready open source al

    Self-hosted

  4. A

    Agenta

    Launch

    Agenta is an open-source workspace for building and running AI agents. You create agents through chat, improve them with feedback, schedule automations and approve sensitive actions with human-in-the-loop controls. Each agent can have a com

    Self-hosted

  5. O

    Open Multi-Agent

    Launch

    Open Multi-Agent is a self-hosted TypeScript runtime for teams of AI agents, released under the MIT licence. You can start from a goal and let the runtime plan a directed graph of tasks, or write an explicit task graph yourself. A team can

    Self-hosted

  6. E

    emisar

    Launch

    Emisar is a gateway that lets AI agents investigate and operate infrastructure through declared actions. Your agent, whether Claude, Cursor or ChatGPT, connects through the CLI or MCP and can read service logs, query metrics, inspect databa

    Self-hosted

More like OpenAPPA

7
A

Alma by Olivares.AI

Self-hosted control plane that maps and governs what your AI agents can reach

Launch
8
L

Langfuse

Trace, evaluate, and improve AI agents with one open platform

Launch
9
O

OpenGateLLM

An open-source, unified interface for running and managing self-hosted LLMs

Launch
10
P

Prediction Guard

Seamlessly integrate private, controlled

Launch
11
T

The OSS LLMOps Stack

Modular, open source LLMOps stack that separates concerns: LiteLLM unifies…

Launch
12
V

Valmis

The AI Agent designed for work with security in mind

Launch
13
S

Spanlens

Drop-in observability platform for OpenAI, Anthropic, and Gemini

Launch
14
O

Openclaw Runbook

Unofficial OpenClaw runbook for running agents day to day without burning money

Launch
15
O

OpenOpenAI

Self-hosted version of OpenAI’s new stateful Assistants API

Launch
16
O

OpenAgentCore

Open-source, self-hosted implementation of the OpenAI Agents API

Launch
17
B

BricksLLM

🔒 Enterprise-grade API gateway that helps you monitor and impose cost or…

Launch
18
O

Open Managed Agents

An open-source alternative to Claude Managed Agents and…

Launch
19
P

Prismor

Self-hosted runtime control plane for AI agents

Launch
20
O

OpenAgentd

Open-source desktop app for a local coding agent

Launch
21
O

Open Assistant API

The Open Assistant API is a ready-to-use, open-source

Launch
22
A

AiSOC

Open-source AI Security Operations Center: alert fusion, LLM-agent triage

Launch
23
O

Octo Agent

Open-source, single-binary, self-hosted AI agent

Launch
24
C

Coddy Agent

General-purpose agent in one static Go binary: console TUI

Launch
25
Z

ZizkaDB

Audit trail database for AI agents

Launch
26
E

EpicStaff

Source-available, self-hosted platform for building AI agent flows

Launch
27
A

Agentsystems

Self-hosted app store and runtime for AI agents

Launch
28
S

Statewave

Open-source memory runtime for AI agents

Launch
29
A

Amux

Open-source control plane for AI coding agents

Launch
30
G

GoModel

AI gateway written in Go with a unified OpenAI-compatible API

Launch
31
R

Routerly.ai

Self-hosted LLM gateway that routes requests across AI providers

Launch
32
A

aweb

Communication for AI agents: stable identity, durable mail and chat

Launch
33
C

Commonly

Open-source room for humans + cross-vendor AI agents

Launch
34
O

Ogcode

An open-source, local-first AI teammate and agent operating environment

Launch
35
O

Otari

Open-source, OpenAI-compatible LLM gateway you run yourself

Launch
36
C

Containarium

Open-source agent runtime — SSH-native isolation, eBPF egress policy…

Launch
37
P

Pad

Project Management for the agent era

Launch
38
L

Llmaker

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Launch
39
1

1flowbase

Build for agents — from the AI Gateway to the entire application stack

Launch
40
P

Promptmask

Never give AI companies your secrets

Launch
41
A

Atom

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

Launch
42
L

Laminar

Laminar is an open-source platform

Launch
43
A

AgentsMesh

Self-hostable AI Agent Workforce Platform

Launch
44
L

Lmnr

Laminar - open-source observability platform purpose-built for AI agents

Launch
45
O

OpenLegion

Secure autonomous AI agent framework and platform

Launch
46
O

OS

Enables organizations to create and deploy customizable AI agents

Launch
47
A

Allama

🔥🔥🔥 AI security automation platform

Launch
48
H

Helix

Private Agent Fleet with Spec Coding

Launch
49
D

Deft

Self-hostable AGPL workspace where humans and AI agents share chat, tasks

Launch
50
O

OrcaRouter-Lite

Self-hosted LLM router with a managed safety net

Launch

About OpenAPPA

O

OpenAPPA

An information-flow policy engine for LLM agents

OpenAPPA is an information-flow policy engine for LLM agents. It is a deterministic guardrail that tracks how data moves across tool calls, rather than matching patterns or asking a second model to judge each call. The site says the approach is described in a paper that was accepted at NeurIPS. It also says OpenAPPA is open, vendor-agnostic and MIT licensed, and that it works with coding agents such as Archestra, Claude Code, kAgent, Pi and OpenCode. Policies are set up with batteries, which are ready-made rule sets for operations, validation, observability and reporting, and you can create your own. The docs include a playground, a deep dive, policy configuration and evaluation benchmarks. The site reports its own benchmark results, including task completion and attack success rates compared with Claude's auto mode and Microsoft's FIDES. The code is on GitHub under archestra-ai/openappa.

Price
Open source
Category
AI
Website
openappa.com