Back to browse
GitHub Repository

An AI workspace inside Neovim where every conversation is a document you own.

55 starsLua

Flemma – a Neovim plugin where the .chat buffer is the conversation

by StanAngeloff·Feb 13, 2026·2 points·0 comments

AI Analysis

●●●BangerWizardrySolve My ProblemNiche Gem

Plain-text `.chat` buffers as agentic state — clever, git-trackable, and genuinely well-implemented.

Strengths
  • `.chat` file IS the state (no SQLite, no shadow logs) — editable, durable, and git-trackable; solves sync-corruption problem elegantly.
  • Autonomous agentic loops with granular approval policies (preview → execute → send) and parallel tool use; stays in user control.
  • Prompt caching and cost tracking across Anthropic/OpenAI/Vertex; filesystem sandboxing limits blast radius of tool execution.
Weaknesses
  • Vim-only; excludes VS Code/Cursor users, who already have Copilot with similar agentic features.
  • Still actively evolving with breaking changes; not yet stable enough for production workflows despite 100+ commits.
Target Audience

Neovim users, AI agent builders, developers who want autonomous code editing with control

Similar To

GitHub Copilot · Continue.dev · Cline

Post Description

Hey HN, I posted Flemma back in October 2025 with no context. Since then I've shipped >100 commits and used it daily as my primary AI workspace so I figured a proper update was due.

The core idea: a .chat file IS the conversation. No SQLite, no JSON logs, no shadow state. What you see in the buffer is exactly what the model receives. Edit an assistant reply to fix a hallucination, delete a tangent, fork by duplicating the file - it all works because there's nothing to fall out of sync.

What's new since October:

- Tool calling. Models can run shell commands, read/edit/write files (same as Pi, just 4 tools). Results go straight into the buffer. There's an approval flow (Ctrl-] cycles: preview -> execute -> send) so nothing runs without your say-so. Parallel tool use also works.

- Prompt caching for Anthropic, OpenAI and Vertex AI. Flemma places cache breakpoints automatically. Long conversations are now significantly cheaper (this was a major pain point for me).

- Extended thinking / reasoning support for all 3 providers.

- Per-buffer overrides via frontmatter. `flemma.opt` lets you pick which tools a buffer can use, set provider parameters, switch models - all scoped to that one file.

- Open registration APIs for both providers and tools. Custom tools can resolve definitions asynchronously from CLI subprocesses or remote APIs. I plan on adding mcporter support at some point.

Flemma works with Anthropic, OpenAI and Vertex AI. You get cost tracking, presets, Lua template expressions, file attachments and a lualine.nvim component.

One thing I want to be upfront about: nearly every line of code in Flemma was written by AI (Claude Code as of late, Amp and Aider in the past). It says so in the README. Every change was personally architected, reviewed and tested by me. I decide what gets built and I vet every diff. I think this is where a lot of software development is heading and I'd rather be honest about it than pretend otherwise.

I'm @StanAngeloff on GitHub - long-time Neovim user and open source enthusiast. Happy to answer questions.

https://github.com/Flemma-Dev/flemma.nvim

Similar Projects

Open Source●●Solid

Rethinking the UI = F(State) Model

Targets fuse data and behavior into ordered, self-contained blocks so your code reads like a sequence (width animates, then color, then fetch) instead of juggling promises and external animation libs. The built-in Web Animations usage and the $$ wait-syntax are neat, opinionated moves — but it's still a bold, niche bet against mature motion ecosystems and will need strong integration stories to win broad adoption.

Big BrainBold Bet
ahmadwasfi
103mo ago
AI/ML●●●Banger

Stateful Inference with 99% Token Savings

Injects raw KV tensors directly into model cache to skip 90% of token recomputation.

Big BrainBold Bet
wasnaga
201mo ago