AI Dev Impact Lab JA
← Topics ranking · 2026-11
GITHUB TOPIC

#ai-research

GitHub repositories that have self-applied the topic "ai-research" — a creator-tagged metadata that surfaces how AI projects describe themselves.

11
tagged repos
16
top 11 stars
3
with tool sigs
11
shown

REPOS Repos for #ai-research (top 11 by stars)

linny006/agent-eval-harness

Live, open-source benchmark for comparing AI coding agents on real GitHub issues

Python ★ 6 AI 90
HudsonCapsuleAI/hris-framework

Open research framework and practical toolkit for studying interaction-shaped behavior, trajectory reconstruction, and long-horizon human–AI collaboration.

★ 5 AI 70 Solo live ↗
mcp-tool-shop-org/research-os

Local-first research control plane for gated source packs, claim truth, contradiction handling, and long-running AI synthesis

TypeScript ★ 2 AI 70 live ↗
grassman23gith/athena-nexus

AI Research Agent 2026 🔍 - Autonomous Deep Web Explorer & Adversarial Synthesis

HTML ★ 2 AI 50
noamt/kir

Keep It Real — a schema-level deferral channel that makes LLM brevity safe. Code, data, and pre-registered protocols: a 400-conversation replication sweep, a placebo control, and a blinded human study (n=46).

HTML ★ 1 AI 70
MinervaRose/agentic-ai-early-projects-portfolio

Agentic AI portfolio: planning agents, multi-agent orchestration, RAG, memory systems, semantic routing, evaluation pipelines, and business workflow automation.

Jupyter Notebook ★ 0 AI 100
yogevat/LLM-TeamGym

Professional multi-agent benchmark library for evaluating LLMs in 23 strategy games — grid, board, social deduction, cards & game theory

Python ★ 0 AI 100
akaalias/ballpark

Autonomous Research with AI: can a UAV learn a city by heart? An AI agent running an autoresearch loop (81 experiments, $364) found a 3.1 MB neural memory that geolocates in-flight pictures of Berlin to ~27 m — no GPS, no map on board, built for a <$5 ESP32-P4 flight computer.

Python ★ 0 AI 70 Solo 1 sig live ↗
0xmdrakib/AgentEvidenceStudio

Replayable agent evidence, conflict-safe memory, and source-bound multi-agent research on flop.

TypeScript ★ 0 AI 70 Solo live ↗
AfonsoZhang/auto-research-system

Claude Code skills for end-to-end CS research: topic selection, literature, experiments, writing and review, with evidence checks, Codex cross-model review and human checkpoints. 科研的门槛,吾辈来拆。

Python ★ 0 AI 70 2 sig
NullLabTests/grounded_evolution

Evaluator-grounded autonomous prompt evolution. Genetic algorithms + runtime validation + meta-evolution to evolve prompts that generate better AI agent code. 150 generations, 862/1000 best score.

Python ★ 0 AI 60 Solo 1 sig live ↗

RELATED Other topics · full topics ranking →

#claude-code

3,787

#ai-agents

3,201

#llm

2,090

#mcp

1,866

#claude

1,854

#python

1,678

#developer-tools

1,530

#codex

1,376

#ai

1,181

Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology