Lithium AI

What it does

Engineering decisions live in people's heads and old PRs. When they leave, it goes with them. New hires and AI tools start from zero every time. Lithium captures those decisions and distributes them to Claude Code, Cursor, and Windsurf via MCP. Add them manually or connect GitHub and they get extracted from merged PRs automatically. Before the AI writes anything, it already knows why your codebase is built the way it is.

Every time an engineer leaves, your team's knowledge leaves with them. Every time a new one joins, their AI tools have zero context. Lithium captures your team's decisions and serves them via MCP.

Engineers leave. Knowledge walks out the door. Lithium captures your team's decisions and distributes them to every AI tool via MCP. The knowledge stays, even when people don't. One config. Every AI tool pulls your decisions before writing code. Claude, Cursor, Windsurf. Same source of truth. Decisions live in clusters that mirror your codebase. auth.tokens, payments.webhooks, infra.deploy. Your AI gets the right context for the file it's editing. New hires inherit every convention from minute one. The tribal knowledge stops dying when the senior engineer goes on vacation. Connect Lithium to GitHub. When a PR merges, AI reads the diff and extracts the decisions worth keeping. Straight into…from getlithium.ai

• 
  ScindoMar 2026 · app.scindo.one · ▲79

  AI captures decisions, drafts plans, and opens matching PRs.

• 
  Fusion2025 · builder.io · ▲297

  One codebase for engineers, designers, PMs, and marketers. Everyone works from one source of truth, on brand and in code, with no handoffs to clean up.

• 
  Aviator Agents2025 · aviator.co · ▲97

  When we asked developers from large engineering teams, almost everyone is using Claude Code, Cursor, or Copilot. But adoption is still inconsistent. Some of us would have 15 agents running in Claude Code at the same time; some would still refuse to use any of them and write code manually. There's a fragmented AI development problem: - Five developers building similar features, and all of them start from scratch - No way to share "here's how we prompt AI to follow our architecture" - No trail of how the AI changes were generated - People leave the company, so does the their knowledge Aviator…

• 
  SkillkitFeb 2026 · agenstskills.com · ▲252

  It's an open-source project that lets you create, translate, and work with multiple agents at the same time, and more.

• 
  XHawk 0.99Mar 2026 · xhawk.ai · ▲237

  Transform Coding Sessions & Code into a System of Context

• 
  GrovDec 2025 · ▲123

  Shared and synchronized AI memory + reasoning across teams

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 18d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 18d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 19d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 21d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 30d ago · world.pixverse.video

• 
  Beam.win▲378

  Run AI agents on one Mac and use its windows on another

  AI · 4d ago · beam.win

• 
  Brew ▲900

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲896

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲806

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲795

  Give your agent a real number and voice to make calls.

  AI · May 2026 · pollyreach.ai

• 
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…

  Life & fun · May 2026 · github.com

• 
  Files.md – Open-source alternative to Obsidian▲730

  🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md

  Dev tools · May 2026 · github.com