SoftCoT
ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning
Compare 3,669 quality-filtered Developer Tools tools using public popularity, activity, licensing and source data.
Browse quality-filtered Developer Tools tools ranked by public signals. Filter by source, pricing, or recency to find a fit faster.
ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning
See what your coding agent actually did. A desktop pal and notch for Claude Code, Codex, Cursor, Gemini CLI and any agent: test results read from the output, fa
AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融
Replace chaotic AI code generation with a disciplined, spec-driven workflow. SDD Pilot enforces structured development phases and quality gates, leveraging AI a
Code graphs, wikis, and research-backed agentic coding. Deterministic tools for nondeterministic workflows, in one opinionated Claude Code config.
TS/JS native Monitoring as Code workflow
Your CLAUDE.md stopped working at 200 lines. Generate scoped skill files from your import graph, auto-sync on every commit. Claude Code, Codex and OpenCode.
Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Kimi, Cursor, Gemini, MinMax, OpenCode, Pi, or Command Code
Context-isolated workflow automation for Pi coding agent
Open source data platform for SQL and Python pipelines, notebooks and dashboards, with type checking, scheduling and definitions in Git.
A local CLI, built on ccusage, that syncs your token usage with everyone else.
Full-configuration CLI for Codex Micro and Work Louder Input: profiles, layers, keymaps, actions, provider handoff, verified apply, and rollback.
OpenScreenShot is a privacy-first, free, open-source screenshot extension -- zero data leaves your device, no account needed, no telemetry, no third-party servi
Lightweight file-based CLI API client with age-encrypted secrets, first-class GraphQL support and MCP server for agentic workflow.
Type one sentence, approve once, walk away — Toh Framework installs an AI build department (14 commands, 8 agents, 23 skills) into your project and keeps buildi
Put Claude Code, Cursor, Codex, Gemini & Antigravity in one room — real-time multi-agent AI collaboration over MCP for distributed dev, code review, PR handoff
An open-source workspace for coding agents, running on your own machine. More work. Less AI waste. Same subscriptions.
The most comprehensive free Claude Code course — 16 phases, 55 modules, EN + VI 🚀
Memory 🧠 to your Personal ChatBot 🤖| LangChainAI and Databutton
Web tasks that compile. Other browser tools tell your AI agent the click worked. chrome-agent reads the page back after every action and answers in JSON what ac
YantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with benchmarked recall, self-tuning ranking, contradiction tracking, proactiv
Official repo for MAI-Code models, where we publish MAI-Code model releases and updates and engage with developer community on issues and feedback.
Upload your files and ask questions about them. Open-source RAG app with LangChain & Streamlit, built before ChatGPT had file uploads. Works with Anthropic & Op
ctx-wire runs your commands, compresses the output with declarative filters, scrubs secrets, and hands your agent a short result. The full log stays on disk for