I recently started a new job and the push for SWE to adopt AI is insane. However, from what I've seen, there's a lot of knowledge that people are sharing through video recordings and demos.
But it's ...
I made a small CLI tool that lets you search through your session history and jump back into old conversations.
Nothing fancy - just searches titles and messages, shows matches, and lets you resume d...
Engineers at @NASAJPL used Claude to plot out the route for Perseverance to navigate an approximately four-hundred-meter path on the Martian surface.
[Announcement Clip](https://x.com/i/status/201731...
I'm heavy Cursor user who pays 1000-2000/m for on demand on top of $200/m Ultra plan.
Got recommended to use CC instead since I mostly use Opus anyway. And yeah, CC is quite fine, can even run it wit...
Craft Agents it's a GUI wrapper for Claude Agent SDK, basically Claude Code with a nice desktop interface. It supports two auth methods:
1. API Key (pay per token)
2. Claude Max OAuth (uses Claude ...
Anthropic is banning Claude Pro/Max users who use third-party coding tools, **and the ToS always said** ***they would.***
There is a recent wave of Claude account suspensions hitting developers who u...
Hey everyone,
I'm a senior software developer and ever since I can remember, I've loved building side projects. Always building something after work or during weekends.
When AI coding tools first ca...
I've got thousands of WordPress posts with valuable information accumulated over years. I want to be able to ask Claude questions and get answers based on all that content rather than having to manual...
Hey all, new Claude user here. Are there any good suggestions or workflows to bring ChatGPT chats and projects into Claude?
I have been setting up MCPs and suddenly Claude Code Desktop does not accept any prompts. Cowork and regular Claude seems to be fine. When removing .mcp.json, it did not help and I have no idea how el...
Anyone have a fix for this? I installed it, clicked to go back on the payment screen to chose a different option, won't load since. I uninstalled the application, deleted cache and restarted. Reinstal...
I'm trying to improve my workflow with Claude Code VSCode extension. What I currently have:
Projectfolder/ (not managed in Git)
├── .claude/settings.local.json
├── CLAU...
Just worked on creating a new skill for Claude and added it to the capabilities. I had an additional, topic related chat and figured "Why not use the findings to further tweak the skill and improve it...
A few days ago my desktop commander MPC start failing within the Claude desktop app and a Windows 10 environment
I have reinstalled Claude desktop and the extension both from the settings panel and f...
I've been an AI engineer for the last three years. Coming from a background of a CS grad that never worked as a software engineer and coming back into CS hardcore with an AI wave, I benefited so much,...
Hi everyone,
I’m a student and have been using Claude for studying, coding, and general research, and it’s been incredibly helpful so far.
I was wondering if there are any current plans, or future p...
Hey everyone! 👋
I've been maintaining a fork of **1Code** (the desktop UI for Claude Code, OpenCode, Codex) and I'm looking for contributors from this community to help keep it going.
**What is 1Cod...
Want to 1-shot larger plans on vanilla Claude Code?
Ask it to:
> use a task agent for each phase if it touches a lot of files, wait for a phase to finish, then `git diff` to make sure it didn't...
Hi there, I id some time ago some devtools, first by hand but then i decided to refactor and improve with claude code. The result seems at least impressive to me. What do you think? What else would be...
We built Nuum because AI coding agents kept forgetting things mid-session. Context windows fill, history gets summarized, and the operational details agents need get compressed away.
**The problem:**...
https://x.com/i/status/2017271756017320197
I build all of my projects in claude.ai, directly in the browser. I recorded this demo in one shot, no pauses. (Great way to bug test a system while work...
Plugins let you bundle any skills, connectors, slash commands, and sub-agents together to turn Claude into a specialist for your role, team, and company.
Define how you like work done, which tools to...
Claude Code hit $1B in run-rate revenue.
Its core architecture? Four primitives: read, write, edit, and bash.
Meanwhile, most agent builders are drowning in specialized tools. One per domain object ...
Hi guys,
I found myself frequently using Deep Research on Claude, however the default **Export to Markdown** feature does not include the urls, which is pretty annoying for me since I need those urls...
# The Problem
Letting AI agents modify your BI tool is terrifying. One bad query and your production dashboards are toast.
# The Solution
Dolt is a MySQL-compatible database with Git semantics. We ...
This is the perfect experience in between tab completion and living in a terminal, and Anthropic needs to jump on this ASAP.
Why not have the ability to spawn async Claude Code instances directly on ...
I’m designing a locally hosted LLM stack that runs entirely on private infrastructure and provides a ChatGPT-style conversational interface. The system needs to work with **structured data stored in M...
Quick setup, free to try, security built-in, full automation features available on Mac and Windows. Connects to Telegram easily, simple setup in under 1 minute.
**Key Features:**
1. Get Orion workin...
[claude](https://preview.redd.it/77q914x4xjgg1.png?width=992&format=png&auto=webp&s=b276635b37c76292b4299d69ed3b7852adf9bf56)
Very good news!
Hey so recently i got very interested into self-hosting LLMs, but i need some guidance, can you tell me which models would be the best choice for me for my specs?
RTX 3070 8GB
32GB DDR5
Ryzen 7 980...
Hey everyone 👋
I just published a \*\*pre-built manylinux wheel\*\* for \`llama\_cpp\_python\` so you can install and use it on Linux without having to compile the native libraries yourself.
📦 \...
Hello. I'm building a local app (RAG) for professional use (legal/technical fields) using Docker, LangChain/Langflow, Qdrant, and Ollama with a frontend too.
The goal is a strict, reliable agent that...
I have been working with NVIDIA H100 clusters at my job for some time now. I became very interested in the local AI ecosystem and decided to build a home server to learn more about local LLM. I want ...
Running latest vllm - nightly build - and is using --tensor-parallel 8 on the setup, and getting about 8-9tps for generating - seems low. I think it should be give or take a tad higher - about 100k co...
I have been working on a side-project which replaces the following things in the Claude ecosystem with free alternatives:
\\- Replaces Anthropic models with NVIDIA-NIM models: It acts as middleware b...
What do you people think is the most useful or interesting MCP server and why?
I think we can all agree though that web search MCP is necessary?
It has been 3-4 days since the big Kimi 2.5 release
Now that we have had a few days what are your experiences with the model?
How does its coding abilities look? Relative to Claude and GLM 4.7?
Ha...
Every single AI chat tool I use - openwebui, msty, claude code etc. all scroll automatically to the bottom the the LLM response requiring you to often scroll back up to the start of the response. This...
https://preview.redd.it/g02kn7n1gjgg1.png?width=618&format=png&auto=webp&s=e965f43fb460517292f2a0d1e9e953421dbbab5e
https://preview.redd.it/5pasy8n1gjgg1.png?width=617&format=png&...
Been using Cursor daily for about 8 months now while building OpenMark, an LLM benchmarking platform. Figured this community would appreciate seeing what's possible with AI-assisted development.
Th...
At work i'm doing thorough reviews but by the time i get to side projects it's like 10pm and the motivation isn't there. i'd vibe code some features, get it working, then remember i should probably ch...
So i used cursor for a month and i was enjoying it to a severely dangerous level. I heard people switch to Claude Code because it offers higher tokens for the same price so i decided to try it.
The ...
Just curious, never used auto , been using 4.5 opus since the release and can't imagine using anything else.
Guys, I shouldn't need to prompt the ai multiple times weekly that I'm on windows, the AI shouldn't forget about this and try commands that don't work on windows, this is one example but I've been usi...
I'm not kidding, I really feel like it's doing more efforts when I press the caps lock button and start calling him the R word
In VS Code i can right click on a function and choose \["Refactor" > "Generate Docs"\] or \["Generate Code" > "Generate Docs"\] and it creates a perfect doc block. It's one of my most used AI fe...
So I’ve been testing different models for code generation without burning tokens too fast, and Auto mode just eats tokens probably because it keeps picking the expensive ones like Opus 4.5.
Does anyo...
Been using the same model for a couple days and suddenly this morning, after a few prompts its depleted my bank. Looking at the usage table it seems to have 100x increased charge per token.
What the ...
for anyone using **Cursor Pro ($20 plan)** and wondering *“what’s the actual limit?”* because Cursor doesn’t show token usage at all and that drove me nuts.
I basically went all-in for one full month...
I will try to share my personal experience with Cursor support, hope it will be useful to a someone. It's my own opinion, no more, no less.
I started to use Cursor actively about half of year ago. ...
Hi, I am trying to move to Cursor IDE from VSCode. I am on a mac, so the default c++ is clang, but I have installed gcc/g++-14. This works fine in VSCode: it both compiles and the intellisense is g++....
## What's changed
- Added tool call failures and denials to debug logs
- Fixed context management validation error for gateway users, ensuring `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` avoids the er...
## What's changed
- Fixed beta header validation error for gateway users on Bedrock and Vertex, ensuring `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` avoids the error
## What's changed
- Added customizable spinner verbs setting (`spinnerVerbs`)
- Fixed mTLS and proxy connectivity for users behind corporate proxies or using client certificates
- Fixed per-user temp...
## What's changed
- Fixed structured outputs for non-interactive (-p) mode
## What's changed
- Added support for full-width (zenkaku) number input from Japanese IME in option selection prompts
- Fixed shell completion cache files being truncated on exit
- Fixed API errors w...
## What's changed
- Added arrow key history navigation in vim normal mode when cursor cannot move further
- Added external editor shortcut (Ctrl+G) to the help menu for better discoverability
- Added...
## What's changed
- Added env var `CLAUDE_CODE_ENABLE_TASKS`, set to `false` to keep the old system temporarily
- Added shorthand `$0`, `$1`, etc. for accessing individual arguments in custom command...
## What's changed
- Fixed crashes on processors without AVX instruction support
## What's changed
- Added new task management system, including new capabilities like dependency tracking
- [VSCode] Added native plugin management support
- [VSCode] Added ability for OAuth users to...
## What's changed
- Added deprecation notification for npm installations - run `claude install` or see https://docs.anthropic.com/en/docs/claude-code/getting-started for more options
- Improved UI re...
Changes since langchain==1.2.6
release: langchain 1.2.7 (#34854)
feat: dynamic tool registration via middleware (#34842)
fix(langchain): strip trailing whitespace from the summarization prompt (#3483...
Changes since langchain==1.2.5
release(langchain): 1.2.6 (#34781)
fix(langchain): `SummarizationMiddleware` signature mismatch & config invocation (#34775)
Changes since langchain==1.2.4
release(langchain): 1.2.5 (#34772)
fix(langchain): add metadata configuration to summarization model invocation (#34763)
feat(langchain): update summarization prompt (#...
Changes since langchain==1.2.3
release: langchain 1.2.4 (#34755)
chore(langchain): add agent name metadata (#34743)
chore: update twitter URLs (#34736)
chore: add tests for private state attr use (re...
Changes since langchain-core==0.3.82
release(core): 0.3.83 (#34733)
feat(core,langchain,text-splitters): (v0.3) use uuid7 for run ids (#34732)
Changes since langchain-core==1.2.6
release: langchain-core 1.2.7 (#34678)
fix: don't trace injected args only found in signature (#34670)
feat(core): add more file extensions to ignore in HTML link ...
Changes since langchain-core==0.3.81
release(core): 0.3.82 (#34688)
fix(core): defer persisting traces for iterator inputs (#34687)
feat(core): add `usage_metadata` to metadata in `LangChainTracer` (...
Changes since langchain==1.2.2
release(langchain): 1.2.3 (#34668)
refactor(langchain): engage summarization based on reported `usage_metadata` (#34632)
fix(langchain): keep tool call / `AIMessage` pa...
Changes since langchain==1.2.1
fix(langchain): add test to verify version (#34644)
release(langchain): release 1.2.2 (#34643)
fix(langchain): handle parallel usage of the todo tool in planning middle...
Changes since langchain==1.2.0
release(langchain): 1.2.1 (#34622)
fix(core,langchain): use `get_buffer_string` for message summarization (#34607)
chore(langchain): fix types in test_model_fallback (#...
## What's Changed
* fix: ensure verbosity flag is applied b
* fix: use response_json_schema
* fix: tool response pt2
## What's Changed
### Features
- Implement before and after tool call hooks in CrewAgentExecutor
- Add structured outputs and response_format support across providers
### Bug Fixes
- Correct tool-ca...
## What's Changed
### Features
- Add structured outputs and response_format support across providers
- Add response_id in streaming response
- Add event ordering and parent-child hierarchy
- Ad...
## What's Changed
### Features
- Add A2A task execution utilities
- Add A2A server configuration and agent card generation
- Add additional A2A transports
- Add Galileo to integrations page
### Bug ...
## What's Changed
### Features
- Add native async chain for a2a
- Add a2a update mechanisms (poll/stream/push) with handlers and config
- Introduce global flow configuration for human-in-the-loop fee...
## What's Changed
### Bug Fixes
- Resolve connection issues (#4129)
### Documentation
- Update api-reference/status docs page
## Contributors
@greysonlalonde, @heitorado, @lorenzejay, @lucasgomide
## What's Changed
### Improvements
- Add `--no-commit` flag to bump command
- Use JSON schema for tool argument serialization
### Bug Fixes
- Fix error message display from response when tool...
## What's Changed
### Features
- Add async flow kickoff
- Add async crew support
- Add async task support
- Add async knowledge support
- Add async memory support
- Add async support for tools and ag...
## What's Changed
### Bug Fixes
- Fix ChatCompletionsClient call to ensure proper functionality (#3910)
- Ensure async methods are executable for annotations
- Fix parameters in RagTool.add, add typi...
## What's Changed
### Features
- Add streaming result support to flows and crews
- Add gemini-3-pro-preview
- Support CLI login with Entra ID
- Add Merge Agent Handler tool
- Enhance flow event state...
## What's Changed
* Fix docs dotnet core typo by @lach-g in https://github.com/microsoft/autogen/pull/6950
* Fix loading streaming Bedrock response with tool usage with empty argument by @pawel-dabr...
## What's Changed
* Update docs for 0.7.3 by @ekzhu in https://github.com/microsoft/autogen/pull/6948
* Update readme with agent-as-tool by @ekzhu in https://github.com/microsoft/autogen/pull/6949
...
## What's Changed
* Update website for 0.7.2 by @ekzhu in https://github.com/microsoft/autogen/pull/6902
* Typo in docs for 'NoOpTracerProvider' by @nicsuzor in https://github.com/microsoft/autogen/...
## What's Changed
* Update website 0.7.1 by @ekzhu in https://github.com/microsoft/autogen/pull/6869
* Update OpenAIAssistantAgent doc by @ekzhu in https://github.com/microsoft/autogen/pull/6870
* ...
## What's New
### `OpenAIAgent` supports all built-in tools
* Feat/OpenAI agent builtin tools 6657 by @tejas-dharani in https://github.com/microsoft/autogen/pull/6671
### Support nested `Team...
# What's New
More helps from @copilot-swe-agent for this release.
### Improvements to `GraphFlow`
Now it behaves the same way as `RoundRobinGroupChat`, `SelectorGroupChat` and others after te...
## What's New
### Streaming Tools
This release introduces streaming tools and updates `AgentTool` and `TeamTool` to support `run_json_stream`. The new interface exposes the inner events of tools...
## Bug Fixes
* Fix bug in GraphFlow cycle check by @ekzhu in https://github.com/microsoft/autogen/pull/6629
* Fix graph validation logic and add tests by @ekzhu in https://github.com/microsoft/autog...
## What's New
### Change to `BaseGroupChatManager.select_speaker` and support for concurrent agents in `GraphFlow`
We made a type hint change to the `select_speaker` method of `BaseGroupChatMana...
## What's New
### `AzureAISearchTool` Improvements
The Azure AI Search Tool API now features unified methods:
- `create_full_text_search()` (supporting `"simple"`, `"full"`, and `"semantic"` q...
- Added support for all GPT-5 models.
- Added support for Grok-4 via `xai/grok-4` and `openrouter/x-ai/grok-4` model names.
- Added support for `gemini/gemini-2.5-flash-lite-preview-06-17` model, by...
#### New Models
- Added support for new Gemini models including `gemini-2.5-pro`, `gemini-2.5-flash`, and `gemini-2.5-pro-preview-06-05` with thinking tokens support.
- Updated model aliases: `flash...
## Model support & provider updates
- Added support for new Claude models including the Sonnet 4 and Opus 4 series (e.g., `claude-sonnet-4-20250514`,
`claude-opus-4-20250514`) across various provi...
- Added support for `gemini-2.5-pro-preview-05-06` models.
- Added support for `qwen3-235b` models.
- Added repo-map support for OCaml and OCaml interface files, by Andrey Popp.
- Added a spinner a...
- Support for GPT 4.1, mini and nano.
- Improved support for using architect mode with Gemini 2.5 Pro.
- Add support for `xai/grok-3-beta`, `xai/grok-3-mini-beta`, `openrouter/x-ai/grok-3-beta`,
...
- Added support for the `openrouter/openrouter/quasar-alpha` model.
- Currently free on OpenRouter.
- Quasar scored 55% on the polyglot coding benchmark
- Run with `aider --model quasar`
- O...
- OpenRouter OAuth integration:
- Offer to OAuth against OpenRouter if no model and keys are provided.
- Select OpenRouter default model based on free/paid tier status if `OPENROUTER_API_KEY` ...
- Added support for SOTA Gemini 2.5 Pro.
- Added support for DeepSeek V3 0324.
- Added a new `/context` command that automatically identifies which files need to be edited for a given request.
- Ad...
- Added support for thinking tokens for OpenRouter Sonnet 3.7.
- Added commands to switch between model types: `/editor-model` for Editor Model, and `/weak-model` for Weak Model, by csala.
- Added...
- Big upgrade in [programming languages supported](https://aider.chat/docs/languages.html) by adopting [tree-sitter-language-pack](https://github.com/Goldziher/tree-sitter-language-pack/).
- 130 ne...