SuperAGI VS sqlfluff

Repo : https://github.com/TransformerOptimus/SuperAGI

The recent introduction of the “Agent Summary” feature in SuperAGI version 0.0.10 has brought a drastic difference in agent performance – improving the quality of agent output. Agent Summary helps AI agents maintain a larger context about their goals while executing complex tasks that require longer conversations (iterations).

Checkout the full release here: https://github.com/TransformerOptimus/SuperAGI/releases/tag/v0.0.10

10. SuperAGI

Currently, PaLM2 Bison is live on the dev branch of SuperAGI GitHub for the community to try: https://github.com/TransformerOptimus/SuperAGI/tree/dev

SuperAGI is made with developers in mind, therefore it takes into account their requirements and preferences when making autonomous AI agents. It has a number of advantages, including:

I think for agents to truly find adoption in real world, agent trajectory fine tuning is critical component - how do you make an agent perform better to achieve particular objective with every subsequent run. Basically making the agents learn similar to how we learn when we

Also I think current LLMs might not fit well for agent use cases in mid to long term because the RL they go through is based on input-best output methods whereas the intelligence that you need in agents is more around how to build an algorithm to achieve an objective on the fly - this requires perhaps new type of large models ( Large Agent Models ? ) which are trained using RLfD ( Reinforcement Learning from demonstration )

Also I think one of the key missing piece is a highly configurable software middle ware between Intelligence ( LLMs ), Memory ( Vector Dbs ~LTMs, STMs ), Tools and workflows across every iteration. Current agent core loop to find next best action is too simplistic. For example if core self prompting loop or iteration of an agent can be configured for the use case in hand. Eg for BabyAGI, every iteration goes through workflow of Plan, Prioritize and Execute or in AutoGPT it finds the next best action based on LTM/STM, or GPTEngineer it is to write specs > write tests > write code. Now for dev infra monitoring agent this workflow might be totally different - it would look like consume logs from different tools like Grafana, Splunk, APMs > See if it doesnt have an anomaly > if it has an anomaly then take human input for feedback. Every use case in real world has it's own workflow and current construct of agent frameworks have this thing hard coded in base prompt. In SuperAGI( https://superagi.com) ( disclaimer : Im creator of it ), core iteration workflow of agent can be defined as part of agent provisioning.

Another missing piece is notion of Knowledge. Agents currently depend entirely upon knowledge of LLMs or search results to execute on tasks, but if a specialised knowledge set is plugged to an agent, it performs significantly better.

Build your own game here: https://github.com/TransformerOptimus/SuperAGI

Repo : https://github.com/sqlfluff/sqlfluff

I'm surprised sqlfluff hasn't been mentioned yet. Perhaps not a comprehensive list, but it's worked for everything I've thrown at it. There's an ANSI keyword list [0], and then dialect-specific lists for everything from DB2 [1] to Snowflake [2].

[0]: https://github.com/sqlfluff/sqlfluff/blob/main/src/sqlfluff/...

It has tons of annoying quirks, but I couldn't imagine running a DBT project without it: https://github.com/sqlfluff/sqlfluff

Move SQL queries to sql files and read from files (Use sqlfluff to lint the code https://github.com/sqlfluff/sqlfluff)

SQLFluff is a good CLI tool for this and includes support for jinja and dbt. I don't think there's a VSCode plugin for it yet.

This linter can really enforce some best practices https://github.com/sqlfluff/sqlfluff

A list of best practices:

BigQuery SQL and SQLFluff

There's a SQL parser/linter called SQLFluff that my team uses for our CI/CD. I've made a few pull requests to fix the parser for the particular SQL dialect we used, and my college compiler classes definitely helped.