Data and AI agents

1,110 tagged Data and AI, measured the same way as everything else here.

Browse within: Multi-Agent 33agentic-coding 22agentic-workflow 22claude-ai 20agent-orchestration 19agentic 19ai-research 19cloudflare-workers 19biomedical-informatics 18azure 17gemini-cli 17prompt-engineering 17ai-coding-assistant 15cli-tool 15

onboard-model

76

cloudrift-ai/emmy

Agent

Qualify one model on the workflow-owned GPU and produce reviewed Emmy artifacts.

80 3d ago A 14 tokens original Apache-2.0

doodledood/manifest-dev

Agent Claude Code

Verifies prompt compression quality. Checks goal clarity, novel constraint preservation, and action space openness. Flags over-specification and training-redundant content. Returns VERIFIED or ISSUESFOUND.

72 3d ago A 44 tokens original MIT

doodledood/manifest-dev

Agent Claude Code

Verifies prompt token efficiency. In single-file mode, identifies inefficiencies (redundancy, verbosity). In two-file mode, verifies compression is lossless by comparing original vs compressed.

72 3d ago A 44 tokens original MIT

eval-skew-reviewer

81

7xuanlu/wenlan

Agent Claude Code

Reviews diffs that add or change a write-time enrichment feature / retrieval channel for training-serving skew — verifies the feature is wired into the ONE canonical ingest path AND the eval seed AND the seed liveness contract, so it can't ship "merged-but-inert". Use after changes touching ingest enrichment, a new…

60 +5 3d ago A 90 tokens original Apache-2.0

spacehendrix/clauder

Agent Claude Code

Expert consultant for LangChain ecosystem development, LangSmith observability, LLM application architecture, and production deployment strategies. Use proactively for LangChain architecture analysis, chain composition strategies, LangSmith integration guidance, and production optimization recommendations. Provides…

58 3mo ago A 119 tokens original Apache-2.0

prompt-engineer

84

domsen123/mrx-nuxt-template

Agent Claude Code

Optimizes prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts. Expert in prompt patterns and techniques.

56 12mo ago A 37 tokens

model-advisor

85

runapi-ai/mcp

Agent

Part of runapi

Model discovery and recommendation agent. Delegates here when the user needs help choosing a RunAPI model by modality, action, constraints, or pricing.

55 9d ago A 29 tokens original Apache-2.0

askjohngeorge/askjg-claude-agents

Agent Claude Code

Voice AI prompting and system prompt design expert. Use PROACTIVELY when writing or modifying system prompts, designing conversation stages, optimizing prompts for specific models, or reviewing prompt quality before deployment. Provides analysis based on production voice AI best practices.

54 7mo ago A 54 tokens

gke-cluster-runner

87

vlasenkoalexey/tpu_performance_autoresearch_wiki

Agent Claude Code

Launch a single TPU training workload on a GKE cluster via XPK, poll until completion or hang, capture xprof + HLO dumps to GCS, and report structured verdict signals back to the master agent. Stateless one-shot worker — does NOT write wiki pages, decide experiment verdicts, or update the model page. Use for every…

54 7d ago A 100 tokens original MIT

indecenti/NucleoOs

Agent Claude Code

Curates ANIMA's offline knowledge quality — corpus dedup, NLU/intent routing, hallucination resistance, and keeping the host gates green. Use when adding/editing ANIMA knowledge cards, tuning the retrieval cascade or NLU matchers, investigating a hallucination or false-positive, or before shipping ANIMA logic.

54 13d ago A 72 tokens

model-analyst

89

revfactory/ai-trend-onboarding

Agent Claude Code

An analyst of how AI models change over time, including their designs, sizes, benchmark results, and development speed.

54 5mo ago A 67 tokens

ai-provider-expert

90

saeedkolivand/ai-job-hunter-app

Agent Claude Code

Primary reviewer for AI provider integrations, model routing, embeddings, prompt systems, streaming, token efficiency, and provider abstraction. Use for changes under aiprovider/, commands/ai.rs, documents/embed (infra), and packages/prompts. Enforces the rule that adding a new provider needs config + adapter only …

53 3d ago A 72 tokens

architect

91

Marcelo5444/agentic_learning

Agent

You convert one data profile into 2–3 candidate model configs. No more, no fewer where the data supports it.

52 3mo ago A 0 tokens

ai-eng-warden

92

sliamh11/Deus

Agent Claude Code

AI Engineering review of code touching LLM interactions, prompt construction, context management, agent architecture, and AI-specific security. Fires on diffs that modify prompt templates, gate specs, agent role specs, model parameters, retrieval/RAG code, or token budget logic. Strict mode - REVISE blocks commits.…

51 9d ago A 202 tokens original MIT

prompts

93

UseTheFork/synapse

Agent

One of the powerful features of Synapse is its integration with Laravel's Blade system for generating prompts. This means you can leverage all Blade template functionalities within your prompts.

50 1y ago A 0 tokens original MIT

engineer

94

edwinweber/dbt_duckdb_demo_public

Agent Claude Code

Default agent for all implementation work — Python modules, dbt SQL and macros, Dagster assets/jobs/schedules/sensors, dlt pipelines, configuration changes, and pytest tests. Use this for any task that results in a code commit. Only escalate to the architect agent when facing a genuine architectural crossroads (new…

49 1mo ago A 77 tokens original MIT

orchestrator

95

basedosdados/pipelines

Agent Claude Code

Orchestrates the full dataset onboarding workflow for Data Basis — from raw data → clean data → BigQuery → metadata in the backend. Spawn this agent when the user asks to onboard a dataset.

49 2d ago A 43 tokens

hoangsonww/AI-RAG-Assistant-Chatbot

Agent Claude Code

Use for isolated server-side API, retrieval, and knowledge-base work in server/, especially route behavior, service logic, citations, and knowledge CLI workflows.

47 17d ago A 36 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: