Accelerating now

underdogs picking up speed
01
tigerless-labs/autoharness
+56% /wk +348 ★/dayaccelerating

This plugin watches your Claude Code sessions, turns recurring patterns into native skills, and quietly archives the ones you stop using.

4.3k Python Coding Assistants · explained Feature
02
Leonxlnx/unlazy
+85% /wk +395 ★/dayaccelerating

unlazy forces AI agents to prove their work through runnable acceptance gates instead of trusting their own exit reports.

3.3k JavaScript Coding Assistants · explained Feature
03
dataelement/dsh-desktop
+76% /wk +620 ★/dayaccelerating

It wraps DeepSeek Harness in a hardened Electron shell so you can run a local-first AI agent without managing CLI child processes or loopback ports.

5.7k TypeScript Agents · explained Feature
04
Player-YN/PawWork_ZhuaZhua
+80% /wk +296 ★/dayaccelerating

Most browser agents chat at you; this one returns editable spreadsheets, slides, and sites you can actually use.

2.6k JavaScript Agents · explained Feature
05
sergebulaev/linkedin-skills
+68% /wk +201 ★/dayaccelerating

Because writing LinkedIn content that sounds human is tedious, this repo packages 11 prompt-engineered skills that let your AI agent draft, audit, and humanize posts—then wait for your approval before publishing.

2.1k Python Coding Assistants · explained Feature
06
wang2122/sprix-sage-router
+66% /wk +349 ★/dayaccelerating

SAGE scores whether an A2A agent should keep a task, recruit complementary teammates, or hand it off entirely—then updates its beliefs from execution evidence.

3.7k Python Agents · explained Feature
07
AMAP-ML/LongHorizon-Harness
+66% /wk +142 ★/dayaccelerating

It stops long-running agents from drifting by forcing them to verify progress through independent roles before every new round.

1.5k Python Agents · explained Feature
08
CopilotKit/OpenBot
+65% /wk +451 ★/dayaccelerating

It exists so you can give AI agents real browsers and tools without giving them the run of the house.

4.8k TypeScript Agents · explained Feature
10
alsk1992/CloddsBot
+65% /wk +234 ★/dayaccelerating

It wires Claude into a thousand trading venues so you can bet on elections, short perps, and launch Solana tokens from a single chat thread.

2.5k TypeScript Agents · explained
11
dsh-market/dsh-market
+61% /wk +328 ★/dayaccelerating

DSH Market adds a browsable, one-click plugin store inside DeepSeek Harness, complete with live theme switching, backup sync, and a diagnostics page that explains why your plugins fight.

3.8k TypeScript Other AI · explained
12
lexmount/moli
+60% /wk +165 ★/dayaccelerating

Moli is a standalone Rust headless browser that avoids continuous rendering by computing layout and paint only when an operation explicitly demands geometry or pixels.

1.9k Rust Agents · explained
13
allenpeng0705/EnvoyMesh
+34% /wk +47 ★/dayaccelerating

EnvoyMesh is a private social network built from your own devices, where a local AI agent chats with friends, negotiates tasks, and shares knowledge without ever hitting a central server.

965 TypeScript Agents · explained
14
elie222/rakazo
+58% /wk +195 ★/dayaccelerating

An open-source Grok Bot alternative where every bot gets a real computer, memory, and the ability to spawn more bots.

2.4k TypeScript Agents · explained
15
zvec-ai/zvec-grep
+39% /wk +189 ★/dayaccelerating

zg indexes your workspace so both terminal users and AI agents can query by meaning or exact text without sending code to the cloud.

3.4k TypeScript RAG · Search · explained
16
uvwt/agentdock
+33% /wk +40 ★/dayaccelerating

It gives AI agents hands-on access to local and remote machines without letting them wander off-leash or consuming a dedicated coding-agent quota.

857 Go Agents · explained
17
melgarafael/DeskcommCRM
+55% /wk +144 ★/dayaccelerating

An open-source alternative to Kommo and Intercom for chat-first businesses, built to self-host AI sales agents that qualify leads and close deals natively over WhatsApp.

1.8k TypeScript Agents · explained
18
XiaoMaColtAI/math-modeling-skill
+27% /wk +58 ★/dayaccelerating

It structures AI agents into a three-role math modeling team—modeler, coder, and writer—enforcing stage-gate quality checks before generating competition-ready Word or LaTeX papers.

1.5k Python Coding Assistants · explained
19
AltanS/collie
+43% /wk +58 ★/dayaccelerating

Collie is a phone web UI that surfaces your Herdr agent herd over Tailscale, ranking agents by who needs you and turning prompts into tappable push notifications.

944 TypeScript Coding Assistants · explained
20
vercel-labs/fx
+42% /wk +175 ★/dayaccelerating

fx exists to provide a tiny, embeddable coding agent that behaves like a Unix shell rather than a bloated terminal IDE, with model-agnostic support for both local and cloud inference.

2.9k Zig Coding Assistants · explained
loading more…

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