InferenceFlow

Prepaid asynchronous LLM inference platform: FastAPI, PostgreSQL-backed queues, deadline-aware scheduling, modular GPU workers, vLLM integration, token metering, ledger billing, Stripe test payments, Next.js dashboard, Python SDK, and Docker. Includes a mock mode and recorded walkthrough; real GPU validation pending

A new way for AI to search for data

View on GitHub

1GitHub stars

136commits on main

0forks

Python 96.1%, TypeScript 2.8%, Shell 0.6%, CSS 0.3% · created 2026-10-22 · last push 2026-10-30

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit be0b3c489b (2026-10-25). main is 80 commits ahead.

Selected work

MANISH AI
@manishklach

“Add hosted mock pipeline audit and owner-encrypted evidence export”. 6 files, 234 lines in scripts, tests.

Licence

The repository

Apache-2.0

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

Apache-2.0, with credit

The author agreed by email on 2026-10-25. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

asynchronousdeveloper-toolsdockerfastapigpuinference-platforminference-servingjob-queue

Example questions

How does InferenceFlow implement asynchronous?
Where does InferenceFlow handle “Add hosted mock pipeline audit and owner-encrypted evidence export”?
Show the developer-tools code in InferenceFlow.

Inside the indexed corpus

Languages by size: Python 96.1%, TypeScript 2.8%, Shell 0.6%, CSS 0.3%, Dockerfile 0.1%.
On GitHub since 2026-10-22, last push 2026-10-30, 136 commits on main.
The pin is 80 commits behind main; the corpus answers from the pinned code, not the newest.

Licence on GitHub and in the corpus

GitHub reported Apache-2.0 for manishklach/InferenceFlow on 2026-10-29, and the LICENSE file at commit be0b3c489b was reviewed as Apache-2.0. They match, so answers from this corpus carry the same terms as the live repository.

Contributors

MANISH AI (@manishklach) has 1 selected repository on the hub.

Using XERJ with InferenceFlow

RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
Best MCP servers for local code search in 2026, compared
Best grep alternative for AI coding agents (2026)
Ask questions about a GitHub repo without cloning it

The prompt

Paste it into your AI agent. It clones manishklach/InferenceFlow at the pinned commit and indexes it on your machine.

Search the GitHub repository manishklach/InferenceFlow with XERJ (https://hub.xerj.org/corpus/manishklach--inferenceflow).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/manishklach/InferenceFlow InferenceFlow && git -C InferenceFlow checkout be0b3c489b656c4e8ceea7cd6af9514e9abb8a07
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./InferenceFlow --url http://127.0.0.1:9200 --prefix inferenceflow --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: Apache-2.0. Keep the copyright notice and credit the authors.

MANISH AI AI, prompts and agents corpora ann-benchmarks agno cognita MrKyaw/Onnx_Rust_Web_Assembly_Triton_Promethus_Grafana aawhan0/ModelDock shuljyli/MXReady

Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.