NoLiMa VS aider

Thanks for the answer, sir. OK, yes. That makes a lot more sense. I am context greedy ever since I read that Adobe research paper that I shared with you months ago. [0]

The whole "context engineering" seems like a thing, though I dislike throwing around the word "engineer" all willy-nilly like that. :)

In any case, thanks for the response. I just wanted to make sure I was not missing something.

[0] https://github.com/adobe-research/NoLiMa

Updated results from the authors: https://github.com/adobe-research/NoLiMa

It's the best known performer on this benchmark, but still falls off even relatively modest context lengths. (Cutting edge reasoning models like Gemini 2.5 Pro haven't been evaluated due to their cost and might be better.)

I only ran the benchmark on Quasar Alpha*; the rest of the scores come from the original paper [0] which was published before 3.7 was available. This is a pretty expensive benchmark to run if you're paying for API usage - I'd actually originally set out to run it on Llama 4 but abandoned that after estimating the cost.

* - I also reproduced the Llama 3.1 8B result to check my setup.

[0] - https://arxiv.org/abs/2502.05167 / https://github.com/adobe-research/NoLiMa*

They are testing for a very straightforward needle retrieval, as LLMs traditionally were terrible for this in longer contexts.

There are some more advanced tests where it's far less impressive. Just a couple of days ago Adobe released one such test- https://github.com/adobe-research/NoLiMa

Aider with a bring-your-own API key has no subscription floor. Pay per token. For 2-3 focused hours per week, costs less than $20/mo. For full-time use, costs more than Max. Best for terminal natives who already live in tmux and do not want a separate IDE.

Aider's GitHub: https://github.com/Aider-AI/aider Lynkr's GitHub: https://github.com/Fast-Editor/Lynkr — star if you want to follow the next integration writeups (OpenHands, Roo Code, Zed are queued).

Look at how the current generation of AI coding tools is built. IDE-integrated agents like Cursor and GitHub Copilot index the open workspace for context. CLI-based agents like Claude Code and Aider operate within a single repository directory. Code intelligence platforms like Sourcegraph Cody can bridge repositories, but doing so requires explicit multi-repo configuration that most teams skip.

Aider is the open-source option. It is a terminal-based pair programmer like Claude Code, but you bring your own model. You can plug it into GPT-4, Claude, or even a local Llama 3 model running on your own machine. The codebase is on GitHub and well maintained.

Aider (aider.chat): Open-source AI pair programmer for the terminal. Works with your git workflow, supports multiple LLM providers, and commits changes automatically.

Aider benchmark harness

OpenCode is a terminal coding agent. It runs in your shell. It has no VS Code extension, no JetBrains plugin, no web UI. When it launched in March 2025 as a Go-based alternative to Aider and Cline, the conventional wisdom was that terminal-only was a deliberate niche — the kind of thing a few vim users would love and the rest of the market would ignore.

Am I misremembering cause I could have sworn that Aider started out as a nvim plugin?? https://github.com/Aider-AI/aider

Aider runs recursive summarization in a background thread using a cheaper "weak model" — a smaller, faster LLM that handles compression while the main model continues reasoning.