ollaya
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench.
No outside reports on file
Ollaya is relatively young with modest adoption (1,386 GitHub stars), so verify its security practices and thoroughly audit any models before using in production, especially with sensitive data.
Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachLocal or standard API callsLOW
- CredentialsNo API token requiredLOW
- Package sourceGitHub (ollaya-dev/ollaya)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/ollaya-dev/ollaya ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-23.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Ollaya
Ollaya is a server that lets you run open-source decision-making models locally, similar to how Ollama works for language models. You can download and serve 25+ model families through a compatible API, running them on your own computer or server instead of relying on cloud services.
Who it’s for
Developers and teams who want to use AI decision models without sending data to external APIs, and who prefer open-source or self-hosted solutions. It's designed for people comfortable with running local servers or Docker containers.
Alternatives
- Ollama (for language models instead of decision models; more mature and widely used)
- LocalAI (open-source AI inference engine with broader model support)
- Hugging Face Transformers (library for running models locally with fine-grained control)
- LM Studio (desktop app for running open models locally with a GUI)
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README for detailed setup instructions. The project supports CLI, desktop app, Docker, and MCP server modes—installation steps vary by your chosen method.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.4k
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Model injection: Malicious models downloaded from untrusted sources could contain hidden code or biased decisions that affect your application's behavior.
- Local system access: Running untrusted models locally gives them potential access to files and resources on your machine, depending on permissions.
- API exposure: If you expose the server on a network or internet-facing port, anyone who finds it could query your models or interfere with them.
- Data in context: Models may retain or leak information from previous queries if not properly isolated between requests.
- Supply chain risk: Dependencies in the project or models it pulls could be compromised, especially since this is a less-established tool than mainstream alternatives.
How to lower the risk
Least-privilege permissions
- Run the server with minimal file system access; use containerization to restrict what the process can read or write.
- Only grant network access to trusted clients.
Network isolation
- Keep the server on localhost or behind a firewall; do not expose it directly to the internet without strong authentication.
- Use a reverse proxy with rate limiting if you must make it remotely accessible.
Monitoring
- Log all model queries and API calls to detect unusual patterns or abuse.
- Monitor CPU, memory, and disk usage—models can be resource-hungry or exploited for denial-of-service.
Red flags to watch for
- Models from unknown or unverified sources; only use models from trusted repositories.
- Sudden changes in model outputs or behavior after updates; verify model integrity.
Questions
How do I install Ollaya?
Ollaya does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/ollaya-dev/ollaya.
Are there security reports about Ollaya?
No reports found for this package in our research (last checked 2026-10-30). Ollaya currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include model injection, local system access, api exposure.
Is Ollaya actively maintained?
Ollaya has 1.4k GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/ollaya-dev/ollaya before pinning it in production.
What are alternatives to Ollaya?
Notable alternatives to Ollaya include Ollama, LocalAI, Hugging Face Transformers, LM Studio. You can also compare Ollaya side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Ollaya? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/ollaya-dev-ollaya)HTML embed:
<a href="https://agentarmorhq.com/skills/ollaya-dev-ollaya"><img src="https://agentarmorhq.com/api/badge/ollaya-dev-ollaya" alt="AgentArmorHQ Risk Grade for Ollaya" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "ollaya-dev-ollaya"Share with your security lead
Need sign-off to use ollaya? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: ollaya
- **Listing URL:** https://agentarmorhq.com/skills/ollaya-dev-ollaya
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.4k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Local or standard API calls
- **Credentials:** No API token required
- **Package source:** GitHub (ollaya-dev/ollaya)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/ollaya-dev/ollaya
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- ollaya-dev
- Source code
- github.com/ollaya-dev/ollaya
- Est. context load
- ~750 tokens / turn (~4 tool schemas, 0.38% of 200k context)
- Popularity
- 1.4k GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-23
Community
Discussions for Ollaya
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude