local-agent
local-administrations-directory
📢 Sondage 2026 : Utilisation des datasets publiques de MediaTech
Vous utilisez ce dataset ou d’autres datasets de notre collection MediaTech ? Votre avis compte !
Aidez-nous à améliorer nos datasets publiques en répondant à ce sondage rapide (5 min) : 👉 https://grist.numerique.gouv.fr/o/albert/forms/gF4hLaq9VvUog6c5aVDuMw/11
Merci pour votre contribution ! 🙌
🇫🇷 French Local Administrations Directory Dataset
This dataset is a processed and embedded version… See the full description on the dataset page: https://huggingface.co/datasets/AgentPublic/local-administrations-directory.local-agentic-coding-bench-8gb-vram-2026-05
agentic coding benchmark: local LLMs on 8GB VRAM
can local LLMs do agentic coding (multi-turn tool calling, file creation, debugging) on consumer hardware? this dataset captures real test results.
hardware
GPU: NVIDIA RTX 4060 Ti 8GB
CPU: Intel i7-14700F
RAM: 32 GB DDR5
OS: Windows 11 + WSL2 (Ubuntu)
inference: llama-server (turboquant fork of llama.cpp)
what was tested
two agent frameworks:
Hermes Agent (NousResearch): structured tool calling with… See the full description on the dataset page: https://huggingface.co/datasets/witcheer/local-agentic-coding-bench-8gb-vram-2026-05.localagent-dispatch-data
LocalAgent Dispatch Data
Synthetic data for training/evaluating a generable tool-dispatch model over a 50-tool surface
(route head → dense selector → pointer-copy). A static snapshot of the deterministic generators in
LocalAgent (src/localagent/data/). Train/eval are
disjoint in both phrasing and slot values. Companion model + demo:
danelcsb/localagent-tiny-30m-byte ·
Space.
Configs
config
rows (train/eval)
what it is
paraphrase
1000 / 1000
many natural… See the full description on the dataset page: https://huggingface.co/datasets/danelcsb/localagent-dispatch-data.local-coding-agent-benchmark
🤖 Local Coding Agent Benchmark (LCAB)
Real-world benchmarking of local AI coding agents on software-repair workloads.
This Hugging Face Dataset contains the reproducibility artifacts, raw agent-session evidence, benchmark results, task source, hardware profiles, and analysis for the Local Coding Agent Benchmark (LCAB).
LCAB is designed to evaluate local coding agents as complete systems—not only by tokens/second, but by how efficiently they transform a real software-repair… See the full description on the dataset page: https://huggingface.co/datasets/amitmaity0/local-coding-agent-benchmark.engosoft-local-code-agent-eval
Engosoft — Local Code Agent: Eval Harness & Findings
Golden-set eval harness and measured findings for building a local coding agent
on Apple Silicon (M5 Pro, 24GB), targeting frontend/backend web work with Arabic
(Egyptian) as a first-class language.
Base model evaluated: mlx-community/Qwen3-Coder-30B-A3B-Instruct-4bit
(30.5B MoE, 3B active, 16.0 GiB at 4-bit).
Headline finding
Injecting a design-system document as a system prompt makes this model worse —… See the full description on the dataset page: https://huggingface.co/datasets/Escanor77/engosoft-local-code-agent-eval.ottoauth-local-agent-snapshot
OttoAuth Local Agent Snapshot
This folder is a minimal Hugging Face-ready snapshot of the OttoAuth browser-agent traces used in the macro-mining experiments.
What is included
raw_traces/: sanitized task.json / trace.json folders copied from the Chrome extension recorder
processed/: the single canonical JSONL used by the Amazon macro study
manifests/: the queued campaign specs that produced these traces
analysis/: the derived Amazon study JSON used for the current… See the full description on the dataset page: https://huggingface.co/datasets/clamepending/ottoauth-local-agent-snapshot.