Alternatives
Products that do what aish does
the terminal your agent can afford to read
- 1
- 2
- 3OA
Scored 65.2% vs google's official 47.8%, and the existing top closed source model Junie CLI's 64.3%. Since there are a lot of reports of deliberate cheating on TerminalBench 2.0 lately (https://debugml.github.io/cheating-agents/), I would like to also clarify a few things 1. Absolutely no {agents/skills}.md files were inserted at any point. No cheating mechanisms whatsoever 2. The cli agent was run in leaderboard compliant way (no modification of resources or timeouts) 3. The full terminal bench run was done using the fully open source version of the agent, no…
Apr 2026 · github.com
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13GF
hi guys. been working on something i think is fundamentally missing in today's workflow with ai agents. vcs. i find myself struggling with questions that agents can't answer like "why did you do it?", "when did u delete this folder? why?", etc. or trying to /rewind (after a /compact...) or basically `bisect` to find when and why something was done by the agent in the current / previous session. just like git did for code, i think we are the same core capabilities with ai agents so... i developed an open source solution for that (currently supporting claude code) would love to…
May 2026 · github.com
- 14
- 15
- 16PS
I originally was just messing with pi-autoresearch. Gave it a sample task to build the most portable coding agent. First cut was 6 KB of shell. Great for one-shots, unusable interactively. I was shocked it actually worked. Started building up -- adding features — but with a self-imposed rule: no new dependencies, and sub 500 LOC. This thing had to be truly portable. Just sh, curl, awk. System primitives only. Which means I did some genuinely disgusting things in awk, including JSON parsing and the OpenAI Responses tool loop with reasoning items carried across turns. It's now ~400 lines. In…
Apr 2026 · pu.dev
- 17
- 18CS
We now write most of our code with agents. For a while, PRs piled up, causing review fatigue, and we had this sinking feeling that standards were slipping. Consistency is tough at this volume. I’m sharing the solution we found, which has become our main product. Continue (https://docs.continue.dev) runs AI checks on every PR. Each check is a source-controlled markdown file in `.continue/checks/` that shows up as a GitHub status check. They run as full agents, not just reading the diff, but able to read/write files, run bash commands, and use a browser. If it finds…
Feb 2026 · docs.continue.dev
- 19
- 20UN
Hi HN, I just released a very simple AI Shell / CLI tool that lets you convert natural language directly into executable shell commands. Built with python to simplify terminal workflows and help you quickly run commands without memorizing syntax. It has two main usage modes: One-shot mode: Quickly execute commands using natural language. Example: ai "find all PNG files larger than 5MB" The AI responds with the appropriate command and asks if you want to execute it. Interactive chat mode: Start a terminal chat session with the AI (ai -i) to iteratively build commands or scripts. Some…
2025 · github.com
- 21
- 22
- 23
- 24AT
In light of recent news about an agent deleting a production database, I thought now would be a good time to share this. As the use of AI tools in production is becoming more common, sadly so will the high profile incidents like the one mentioned. Fewshell is a terminal agent specifically designed to avoid this. There is no setting to enable command auto-approval. This is by-design, so that the user never has to second-guess or worry about accidentally having it enabled. Originally my intention was to build an AI mobile terminal to make typing shell commands easy. But with so many…
Apr 2026 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →