RepoRadar
Leave a Tip
Item detail
github.com

Sentdex/minion

Sentdex/minion is a single-file low-context coding a that RepoRadar is tracking in its MIT single-file (~3400 lines) Python coding agen section, currently rated Gold tier with a 'try now' verdict. Its strongest signal is workflow potential, scored 9.1 out of 10.

Open source →Back to radar
Score8.0
Popularity186.0
Risknone
TierGold
Score breakdown
Usefulness9.0
Novelty8.0
Momentum8.0
Maturity8.8
Open-source/build8.4
Evidence8.0
Workflow potential9.1
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for AI-power-users who run coding agents on local LLMs (Qwen / Llama / Hermes / Mistral on llama.cpp / vLLM / SGLang) and want a coding agent that does not waste the first 50K of context on every turn — minion sends ~625 tokens on a bare `hey` (vs 20K-50K for harness-heavy agents), and the context savings are paid on every single turn; for self-hosters who want a single-file (~3400 lines) a

Who should use it

AI-power-users who run coding agents on local LLMs (Qwen / Llama / Hermes / Mistral on llama.cpp / vLLM / SGLang) and want a coding agent that does not waste the first 50K of context on every turn — minion sends ~625 tokens on a bare `hey` (vs 20K-50K for harness-heavy agents), and the context savings are paid on every single turnSelf-hosters who want a single-file (~3400 lines) agent they can read end-to-end and modify without learning a framework — no TUI framework, no plugin system, no config file format, raw terminal escapes for the interfaceEngineering teams evaluating cost per turn — every turn on a hosted API is cheaper when the harness does not eat the first 50K of context, and the difference compounds over long sessionsEngineering teams who want a token-floored baseline to compare against — minion prints a token footer on every turn so the number you see is the number that rides along every messageUsers who want a coding agent that works against any OpenAI-compatible endpoint without rewriting glue code — minion talks directly to the OpenAI SDK and reads from env varsUsers who want the simplest possible install path — no package manager, no node_modules, just `pip install openai` and run `minion.py`Evaluation: clone the repo, set `OPENAI_API_BASE=http://localhost:8080/v1` (or your hosted endpoint), set `OPENAI_API_KEY=***` (or empty for local), run `python minion.py`, type `hey`, and read the token footer at the bottom of the prompt

Who should skip it

Move on from Sentdex/minion if the licensing terms, language support, or platform requirements do not fit your project.

About this signal

Sentdex/minion is tracked by RepoRadar as a single-file low-context coding a in the MIT single-file (~3400 lines) Python coding agen section. It was first seen on 2026-06-25 and last updated on 2026-06-25. The current verdict is 'try now' with a Gold tier and easy setup difficulty. Across RepoRadar's eight signals, Sentdex/minion is strongest on workflow potential (9.1) and practical usefulness (9.0) and weakest on evidence quality (8.0) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned Sentdex/minion a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 186.0 and never affects the composite score or tier. The risk label of 'none' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.

Risk explanation

No inherent user-impacting risk is flagged from the captured evidence.

Evidence links

Closest alternatives / related signals

  • No close related item is available in the current public catalog.
minionsentdexharrison-kinsleysingle-file3400-lineslow-context625-tokenscontext-bloat