LLMOps · Eval

LLMOps · Eval

heavyweights · gaining speed
01
chopratejas/headroom
+1941 ★/dayaccelerating

A local compression layer that sits between your agent and the LLM, cutting token counts by routing tool outputs, logs, and code through type-specific compressors.

21.8k Python LLMOps · Eval · explained Feature
02
mvanhorn/last30days-skill
+1723 ★/dayaccelerating

A skill that turns Claude, Cursor, or any agent host into a social-native research analyst, scoring signals by upvotes, likes, and actual money wagered.

39.1k Python Coding Assistants · explained Feature
03
NousResearch/hermes-agent
+1680 ★/dayaccelerating

Hermes Agent is a self-improving AI assistant that creates skills from experience, persists knowledge across sessions, and runs anywhere from a $5 VPS to serverless cloud.

190k Python Agents · explained Feature
04
harry0703/MoneyPrinterTurbo
+942 ★/dayaccelerating

A Python pipeline that turns a keyword into a complete short-form video—script, stock footage, voiceover, subtitles, and all.

85.1k Python Creative · Design · explained
05
farion1231/cc-switch
+1052 ★/dayaccelerating

Desktop app that corrals Claude Code, Codex, Gemini CLI and half a dozen other AI agents into one switchboard.

97.6k Rust Coding Assistants · explained
06
CopilotKit/CopilotKit
+385 ★/dayaccelerating

A React SDK that lets AI agents render UI mid-thought and ask humans for help before continuing.

34.6k TypeScript Agents · explained
07
aaif-goose/goose
+353 ★/dayaccelerating

Goose is a Rust-built, open-source agent that edits code, runs commands, and connects to 70+ tools via MCP — not just another chat wrapper.

48.8k Rust Agents · explained
08
Andyyyy64/whichllm
+261 ★/dayaccelerating

whichllm ranks local models by real benchmark scores, not parameter count, and tells you which ones actually fit your hardware.

4.4k Python Inference · Serving · explained
09
pbakaus/impeccable
+484 ★/dayaccelerating

23 slash commands and 27 anti-pattern rules that teach Cursor, Claude, and Copilot how to design instead of defaulting to Inter and purple gradients.

37.2k JavaScript Coding Assistants · explained
10
supermemoryai/supermemory
+229 ★/dayaccelerating

Supermemory is a hosted memory layer that lets LLMs remember facts, preferences, and context across conversations instead of starting from scratch every time.

26.5k TypeScript RAG · Search · explained
11
lyogavin/airllm
+162 ★/dayaccelerating

AirLLM slices giant transformers into layer shards so they fit in consumer VRAM without quantization or distillation.

19.8k Jupyter Notebook Inference · Serving · explained
12
QuantumNous/new-api
+200 ★/dayaccelerating

A Go-based gateway that cross-converts between OpenAI, Claude, and Gemini formats so you don't have to pick sides in the API format wars.

38.2k Go Inference · Serving · explained
13
hardikpandya/stop-slop
+213 ★/dayaccelerating

A meta-writing tool that uses structured rules and a 50-point rubric to strip AI-generated prose of its telltale tics.

9.9k LLMOps · Eval · explained
14
HKUSTDial/Supervisor-Skills
+148 ★/dayaccelerating

An HKUST professor bottled a decade of top-conference publishing and reviewing experience into structured AI prompts for grad students.

2.3k Python LLMOps · Eval · explained
16
oracle-devrel/oracle-ai-developer-hub
+68 ★/dayaccelerating

A curated hub of notebooks, apps, and guides that treat Oracle AI Database as the single backbone for vectors, graphs, memory, and SQL.

4.1k Jupyter Notebook Agents · explained
17
Imbad0202/academic-research-skills
+484 ★/dayaccelerating

Claude Code skills that run your research through a full academic pipeline—research, writing, staged integrity checks, and multi-perspective review—while keeping a human in the driver's seat.

29.9k Python Coding Assistants · explained
18
AstrBotDevs/AstrBot
+95 ★/dayaccelerating

AstrBot is a Python framework for wiring LLMs into QQ, WeChat, Telegram, Slack, and a dozen other chat platforms without writing platform glue.

34.4k Python Agents · explained
19
BerriAI/litellm
+115 ★/dayaccelerating

LiteLLM is the adapter layer that stops your codebase from fracturing across a dozen provider SDKs.

50k Python LLMOps · Eval · explained
20
Wei-Shaw/sub2api
+275 ★/dayaccelerating

An open-source gateway for splitting AI subscriptions across teams without breaking native tools.

27k Go LLMOps · Eval · explained
loading more…

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.