OpenAPPA
OpenAPPA is a deterministic guardrail that sits between an AI agent and its tools and tracks how data flows across tool calls, instead of asking a second model to judge each call. Policies decide whether untrusted or sensitive data may reach a given action, which blocks data exfiltration caused by prompt injection or hallucination while letting agents finish their tasks. It plugs into Claude Code, Pi, OpenCode, kAgent and Archestra, comes with reusable policy "batteries", validation, observability and reporting, and is backed by a NeurIPS workshop paper with published benchmarks. It is in preview as an open RFC.
Updated
✨ Try AgentScout's free AI image generator →Good for: evaluating agents, monitoring agents in production, agent security and safety
Official channels
Use cases
About OpenAPPA
OpenAPPA is listed in our security & governance category and is aimed at builders. OpenAPPA is a deterministic guardrail that sits between an AI agent and its tools and tracks how data flows across tool calls, instead of asking a second model to judge each call. Policies decide whether untrusted or sensitive data may reach a given action, which blocks data exfiltration caused by prompt injection or hallucination while letting agents finish their tasks. It plugs into Claude Code, Pi, OpenCode, kAgent and Archestra, comes with reusable policy "batteries", validation, observability and reporting, and is backed by a NeurIPS workshop paper with published benchmarks. It is in preview as an open RFC. Pricing, as the maker states it: Free and open source (MIT); preview and RFC. Maturity: Active. We last checked the official link on 2026-10-21.
OpenAPPA at a glance
- Category: Security & governance
- Built for: Developers and teams building with AI agents
- Pricing: Free and open source (MIT); preview and RFC (as the maker states it)
- GitHub: archestra-ai/OpenAPPA · 1,596 stars (as of Oct 21, 2026)
- Official site: openappa.com
- Listed on AgentScout: Oct 21, 2026
OpenAPPA FAQ
What is OpenAPPA?
OpenAPPA is a deterministic guardrail that sits between an AI agent and its tools and tracks how data flows across tool calls, instead of asking a second model to judge each call. Policies decide whether untrusted or sensitive data may reach a given action, which blocks data exfiltration caused by prompt injection or hallucination while letting agents finish their tasks. It plugs into Claude Code, Pi, OpenCode, kAgent and Archestra, comes with reusable policy "batteries", validation, observability and reporting, and is backed by a NeurIPS workshop paper with published benchmarks. It is in preview as an open RFC.
How much does OpenAPPA cost?
OpenAPPA's pricing, as the maker states it: Free and open source (MIT); preview and RFC. Check the official site for current plans.
Where can I find OpenAPPA's source code?
On GitHub at archestra-ai/OpenAPPA, which had 1,596 stars as of Oct 21, 2026.
What are alternatives to OpenAPPA?
Similar tools include Superagent, ThinkWatch Lite, Halofy, PentAGI, Eleven and Pragor.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
OpenAPPA ratings and reviews
OpenAPPA alternatives
Other security & governance tools in our directory. See all security & governance tools →
Superagent
SDK for AI agent safety that blocks prompt injections and unsafe tool calls, redacts PII and secrets, and runs red-team scenarios.
ThinkWatch Lite
A local gateway that sits between your coding agents and model providers, letting you switch upstreams, redact secrets before they leave your machine, block dangerous tool calls and see the cost of each request.
Halofy
Halofy is an access and governance layer for a team's AI agents, giving every agent organizational context through one identity and policy model with provenance and audit, alongside a desktop AI workstation that turns power users' agent practices into shared policies.
PentAGI
Autonomous multi-agent system for running penetration testing tasks.
Eleven
An agent-first reverse-engineering app for macOS, Windows and Linux: load any app or binary and ask your AI agent what it does while it disassembles and analyzes the code for you.
Pragor
Coordination and governance layer for teams of people and AI agents, not an autonomous agent: a shared board with tasks, directed messages, approvals, files and an attributable activity record, where agents connect over REST or project MCP access.
Related lists
🏆 See also: Strix alternatives · All best-of lists
🧭 Task guides: Guardrail and policy tools for agent security · AI eval and benchmark tools
Badge for makers
Built OpenAPPA? Add this badge to your README or site. It links back to this page. About badges
