Organization repository on GitHub
Ollama with POST /v1/systemone for Drex DLM.
- Forks
- 1
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Integrations & Adapters
Ollama (nace-ai fork)
A fork of Ollama that adds POST /v1/systemone: the endpoint is forwarded to a custom llama-server from nace-ai/llama.cpp on the edlm branch, which serves Drex DLM. The fork is MIT licensed and Go-based like upstream Ollama.
- Stars
- 5
- Language
- Go
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- nace-ai
- Last verified
- Oct 2026
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- Go
- Capabilities
- Open sourceSelf-hostedRuns locally
Highlights
- Adds POST /v1/systemone to Ollama, forwarded to a custom llama-server that serves Drex DLM.
- The llama-server comes from nace-ai/llama.cpp on the edlm branch, built with cmake presets.
- Presets: darwin for Apple Silicon, llama_cuda_v12_linux for NVIDIA Linux, cpu for CPU builds.
- OLLAMA_LLAMA_CPP_SOURCE must point at the llama.cpp source before cmake -S; released Ollama binaries do not read it.
- MIT licensed Go fork; created 2026-10-01 and pushed 2026-10-14, 4 stars when the sweep ran.
Quickstart
bash
export OLLAMA_LLAMA_CPP_SOURCE=/path/to/llama.cpp
cmake -S llama/server --preset darwin
cmake --build build/llama-server-darwin --target llama-server --parallel 8Watch out
README reviewed 2026-10-17; the digest excerpt mixes the fork's added section with the standard Ollama install text and never describes Drex DLM's own capabilities, so this entry covers only the routing of /v1/systemone.
Questions about this entry
Short answers drawn from the linked project or page.
A fork of Ollama that adds a POST /v1/systemone endpoint. The endpoint is forwarded to a custom llama-server from nace-ai/llama.cpp on the edlm branch, which serves Drex DLM.
The README says POST /v1/systemone is forwarded to llama-server from nace-ai/llama.cpp, branch edlm, which the fork builds as a separate binary and launches; the rest of Ollama behaves like upstream.
Export OLLAMA_LLAMA_CPP_SOURCE to the llama.cpp source path, then run cmake -S llama/server --preset darwin and cmake --build build/llama-server-darwin --target llama-server --parallel 8 for Apple Silicon.
Apple Silicon uses darwin with build/llama-server-darwin; NVIDIA Linux uses llama_cuda_v12_linux with build/llama-server-cuda_v12; CPU uses cpu with build/llama-server-cpu.
The README warns to set the source variable before cmake -S because a released Ollama binary does not read it; without it the build cannot use the fork's custom llama-server sources.
The digest does not describe other changes: the added section covers serving Drex DLM through /v1/systemone, and the remaining README text is the standard Ollama download and install content.
The nace-ai organization publishes it as a Go project under the MIT license. The repository was created 2026-10-01 and last pushed 2026-10-14, with 4 stars when the sweep ran.
More Jev resources like this
An Ollama-style local runner for System One decision models from Hugging Face: pull, serve and query them behind the same /v1/systemone API as TypeSafe's Jev, with a terminal model manager and a browser playground.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
nvkudva/ollajevPython
nvkudva/ollajevPythonA CLIProxyAPI plugin that routes System One decision requests to any compatible node, a local model server such as Winnow 12B or hosted lanes like OpenCode, OpenRouter and v1m, chosen by model prefix, with a management UI.
Jev Integrations & Adapters#community#github#gateway
Community
ducdao98z/cpa-plugin-systemoneGo
ducdao98z/cpa-plugin-systemoneGoA TypeScript project that wraps DeepSeek's FIM API or llama.cpp's Completion API into a Jev / TypeSafe SystemOne-style discrete decision interface, published on npm as @lenml/jevseek with a WebUI and Docker workflow.
Jev Integrations & Adapters#community#github#deepseek
Community
lenml/deep-jev-seekTypeScript
lenml/deep-jev-seekTypeScriptA local, CPU-only Jev-Style-0.8B-Decision-v3 service with an oh-my-pi extension that points the agent's typesafe judge provider at it over loopback HTTP. No GPU, no API key, and the 505 MiB model is fetched separately.
Jev Integrations & Adapters#community#github#local
Community
7n1m4/jevShell
7n1m4/jevShellReal-time geopolitical intelligence dashboard that uses TypeSafe Jev questions to score news headline severity into five threat levels and categorize events across 14 conflict, cyber and infrastructure domains, alongside news aggregation and a Country Instability Index.
Jev Integrations & Adapters#community#osint#geopolitics
Community
koala73/worldmonitorTypeScript
koala73/worldmonitorTypeScriptPrivacy-first, self-hosted personal knowledge management system with block-level references and a local-first Markdown editor; the project integrates Jev's decision model for high-speed document classification, flashcard intent categorization and automated tag routing.
Jev Integrations & Adapters#community#note-taking#knowledge-base
Community
siyuan-note/siyuanTypeScript
siyuan-note/siyuanTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.