Harman's banner

Harman

@itsharmanjot • 5,059 subscribers

Daily content on AI, No-Code & emerging tech • Learn practical AI tools to grow faster and work smarter • DM for partnerships & collabs

Shorts

EVERYONE'S TRYING TO SOLVE AI TEAM MEMORY WITH SERVERS, VECTOR DATABASES, AND ORCHESTRATION PLATFORMS. THIS OPEN SOURCE TOOL DOES IT WITH ONE FOLDER IN YOUR REPO. Every dev on your team runs Claude Code. When one agent screws something up, the rest have no idea. They just repeat the mistake next week. It's called teamlore. When your agent gets corrected or breaks something, it writes a small lore file into a .lore/ folder. That file ships with your PR, gets reviewed like normal code, and after merge every teammate's agent automatically recalls it when they touch that part of the repo. No server. No datab No accounts. No SaaS bill. Just a folder in git. Which means code review catches bad lessons before they poison the team, git blame tells you when a rule was added and why, and the whole thing works offline. One command to install: npx teamlore init Companion command: npx teamlore scarmap. Turns your team's history of mistakes into a visual heat map of the codebase. Every red zone is a place your team has been burned before. Which means every red zone is a place your agents should slow down. Here's the wildest part. The teamlore repo's own .lore/ folder contains every mistake Claude made while building teamlore itself. Dogfooded end-to-end. You can literally open the folder and read the receipts. The author's public invitation: "Would love for someone to try and break it." Available on npm. Repo just launched. 100% open source. (link in the comments)

EVERYONE'S TRYING TO SOLVE AI TEAM MEMORY WITH SERVERS, VECTOR DATABASES, AND ORCHESTRATION PLATFORMS. THIS OPEN SOURCE TOOL DOES IT WITH ONE FOLDER IN YOUR REPO. Every dev on your team runs Claude Code. When one agent screws something up, the rest have no idea. They just repeat the mistake next week. It's called teamlore. When your agent gets corrected or breaks something, it writes a small lore file into a .lore/ folder. That file ships with your PR, gets reviewed like normal code, and after merge every teammate's agent automatically recalls it when they touch that part of the repo. No server. No datab No accounts. No SaaS bill. Just a folder in git. Which means code review catches bad lessons before they poison the team, git blame tells you when a rule was added and why, and the whole thing works offline. One command to install: npx teamlore init Companion command: npx teamlore scarmap. Turns your team's history of mistakes into a visual heat map of the codebase. Every red zone is a place your team has been burned before. Which means every red zone is a place your agents should slow down. Here's the wildest part. The teamlore repo's own .lore/ folder contains every mistake Claude made while building teamlore itself. Dogfooded end-to-end. You can literally open the folder and read the receipts. The author's public invitation: "Would love for someone to try and break it." Available on npm. Repo just launched. 100% open source. (link in the comments)

34,614 views

I replaced our Datadog bill with a single binary and cut infrastructure costs by 98% overnight. It’s called OpenObserve. Logs, metrics, traces, and frontend monitoring in one tool, self-hosted, and it’s built specifically to stop the bill that grows every time you add a host, a user, or a custom metric. → One binary, running in under 2 minutes. No cluster, no separate components for logs vs metrics vs traces → Built in Rust on the DataFusion query engine, so it stays fast even at petabyte scale → Uses Parquet columnar storage on S3-compatible object storage instead of a proprietary format, which is where the real cost savings come from → Query with SQL or PromQL instead of a vendor’s proprietary syntax, so your team isn’t learning a new query language just to read a dashboard → Full OpenTelemetry compatibility, no proprietary agents required to get your existing instrumentation talking to it → Community dashboard library on GitHub for Kubernetes, Docker, Postgres, AWS, and LLM observability, ready to drop in instead of building from scratch In OpenObserve’s own published benchmark, the same 16-service workload cost $174/day on Datadog and $3/day self-hosted, a 98% cut, before even touching per-host or per-seat fees. 18,000+ GitHub stars. Single binary. Self-hosted, no per-host or per-user tax.

I replaced our Datadog bill with a single binary and cut infrastructure costs by 98% overnight. It’s called OpenObserve. Logs, metrics, traces, and frontend monitoring in one tool, self-hosted, and it’s built specifically to stop the bill that grows every time you add a host, a user, or a custom metric. → One binary, running in under 2 minutes. No cluster, no separate components for logs vs metrics vs traces → Built in Rust on the DataFusion query engine, so it stays fast even at petabyte scale → Uses Parquet columnar storage on S3-compatible object storage instead of a proprietary format, which is where the real cost savings come from → Query with SQL or PromQL instead of a vendor’s proprietary syntax, so your team isn’t learning a new query language just to read a dashboard → Full OpenTelemetry compatibility, no proprietary agents required to get your existing instrumentation talking to it → Community dashboard library on GitHub for Kubernetes, Docker, Postgres, AWS, and LLM observability, ready to drop in instead of building from scratch In OpenObserve’s own published benchmark, the same 16-service workload cost $174/day on Datadog and $3/day self-hosted, a 98% cut, before even touching per-host or per-seat fees. 18,000+ GitHub stars. Single binary. Self-hosted, no per-host or per-user tax.

50,356 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Local models just got a free intelligence upgrade. Someone took the new Qwen3.8-27B (the one that already runs in 22GB) and only changed the chat template. No fine-tune. No new training. Just a smarter system prompt that kills all the filler and forces the model to stay sharp. Result: the same weights are now fixing real post-cutoff bugs faster and cleaner than Claude Opus 5 High in their tests. They call it the Sharp template. It’s free. Drop it on any Qwen3.5 / 3.6 / 3.8 model and it just works with llama.cpp. This is the kind of quiet upgrade that actually moves the needle for people running models locally.

Local models just got a free intelligence upgrade. Someone took the new Qwen3.8-27B (the one that already runs in 22GB) and only changed the chat template. No fine-tune. No new training. Just a smarter system prompt that kills all the filler and forces the model to stay sharp. Result: the same weights are now fixing real post-cutoff bugs faster and cleaner than Claude Opus 5 High in their tests. They call it the Sharp template. It’s free. Drop it on any Qwen3.5 / 3.6 / 3.8 model and it just works with llama.cpp. This is the kind of quiet upgrade that actually moves the needle for people running models locally.

73,030 views • 6 days ago

384GB of VRAM. On your desk. Not in a datacenter. Autonomous, the company behind SmartDesk, just open sourced complete build guides for a personal AI computer that runs open models on hardware no one can switch off. It's called Autonomous Computer. Three configurations, one philosophy: a model you rent can be cut off overnight. A model running in your own house can't. → Home build: 2x RTX 5090 workstation → Team build: 4x RTX PRO 6000 Blackwell, 384GB VRAM → On-prem business build: 8x RTX 4090/5090, up to 256GB VRAM Every config ships with the full bill of materials, 3D printable and CNC housing files, wiring diagrams, BIOS tuning, and assembly photos. Software side covers OS setup, NVIDIA drivers, and serving open models through Ollama, vLLM, and llama.cpp. Fork it. Change it. Build it. Sell it. MIT License. 100% Opensource. Repo:

384GB of VRAM. On your desk. Not in a datacenter. Autonomous, the company behind SmartDesk, just open sourced complete build guides for a personal AI computer that runs open models on hardware no one can switch off. It's called Autonomous Computer. Three configurations, one philosophy: a model you rent can be cut off overnight. A model running in your own house can't. → Home build: 2x RTX 5090 workstation → Team build: 4x RTX PRO 6000 Blackwell, 384GB VRAM → On-prem business build: 8x RTX 4090/5090, up to 256GB VRAM Every config ships with the full bill of materials, 3D printable and CNC housing files, wiring diagrams, BIOS tuning, and assembly photos. Software side covers OS setup, NVIDIA drivers, and serving open models through Ollama, vLLM, and llama.cpp. Fork it. Change it. Build it. Sell it. MIT License. 100% Opensource. Repo:

47,954 views • 1 month ago

Alibaba just released a coding model that hits 82 percent on SWE-Bench Verified. That is the highest score ever published for an open-source model. The weights are free. The license is Apache 2.0. You can run it today. The model is Qwen 4 Coder 32B. Here is what 82 percent on SWE-Bench Verified actually means. SWE-Bench Verified tests whether an AI can autonomously resolve real bugs pulled from real production GitHub repositories. Not synthetic exercises. Real open-source projects that real teams depend on. A model gets a bug report, reads the code, writes a fix, and either passes the test suite or it does not. At 82 percent, Qwen 4 Coder 32B resolves 82 out of every 100 real production bugs it is given. Without a human guiding it. On code it has never seen before. For comparison: Qwen 4 Coder 32B: 82 percent SWE-Bench Verified. Open source. Apache 2.0. Claude Fable 5: 80.3 percent SWE-Bench Pro. $10 input / $50 output per million tokens. Currently suspended. GPT-5.6 Sol: Competitive on Terminal-Bench. $5 input / $30 output per million tokens. An open-weight model that you can download and run for free just beat both of them on the benchmark designed to measure real software engineering capability. Here is the architecture. Qwen 4 Coder 32B is a 32 billion parameter dense model. Not a Mixture-of-Experts. Every parameter is active on every request. This matters for inference: a dense 32B model runs on 22 gigabytes of VRAM, which fits on a single high-end consumer GPU or a MacBook Pro with 64GB of unified memory. The smaller variant, Qwen 4 Coder 4B, runs at approximately 135 tokens per second on an M5 Max and fits inside 8 gigabytes of RAM. For a model with usable coding capability, that is a new bar for what fits in a single laptop. The training methodology continued Alibaba's approach of reinforcement learning on verifiable coding tasks. The model gets rewarded when its code passes tests. It gets penalized when it fails. Over millions of training steps, the model learns to write code that actually runs rather than code that looks plausible. License: Apache 2.0. Full commercial use. No attribution requirement. No revenue threshold. No monthly active user ceiling. Weights: Hugging Face, available today. Runs on: vLLM, Ollama, SGLang, and any standard GGUF-compatible inference engine. Qwen 4 32B also runs at approximately 135 tokens per second on an M5 Max chip, setting a new bar for what a sub-8GB model can do on Apple Silicon. The open-source coding model just beat the best closed-source model in the world on the benchmark designed to test whether AI can actually do software engineering. The weights are free. The subscription is optional. Source: Autom8Labs AI Insight July 2026, State of Open Source LLMs June 2026, Kunal Ganglani blog June 2026.

Alibaba just released a coding model that hits 82 percent on SWE-Bench Verified. That is the highest score ever published for an open-source model. The weights are free. The license is Apache 2.0. You can run it today. The model is Qwen 4 Coder 32B. Here is what 82 percent on SWE-Bench Verified actually means. SWE-Bench Verified tests whether an AI can autonomously resolve real bugs pulled from real production GitHub repositories. Not synthetic exercises. Real open-source projects that real teams depend on. A model gets a bug report, reads the code, writes a fix, and either passes the test suite or it does not. At 82 percent, Qwen 4 Coder 32B resolves 82 out of every 100 real production bugs it is given. Without a human guiding it. On code it has never seen before. For comparison: Qwen 4 Coder 32B: 82 percent SWE-Bench Verified. Open source. Apache 2.0. Claude Fable 5: 80.3 percent SWE-Bench Pro. $10 input / $50 output per million tokens. Currently suspended. GPT-5.6 Sol: Competitive on Terminal-Bench. $5 input / $30 output per million tokens. An open-weight model that you can download and run for free just beat both of them on the benchmark designed to measure real software engineering capability. Here is the architecture. Qwen 4 Coder 32B is a 32 billion parameter dense model. Not a Mixture-of-Experts. Every parameter is active on every request. This matters for inference: a dense 32B model runs on 22 gigabytes of VRAM, which fits on a single high-end consumer GPU or a MacBook Pro with 64GB of unified memory. The smaller variant, Qwen 4 Coder 4B, runs at approximately 135 tokens per second on an M5 Max and fits inside 8 gigabytes of RAM. For a model with usable coding capability, that is a new bar for what fits in a single laptop. The training methodology continued Alibaba's approach of reinforcement learning on verifiable coding tasks. The model gets rewarded when its code passes tests. It gets penalized when it fails. Over millions of training steps, the model learns to write code that actually runs rather than code that looks plausible. License: Apache 2.0. Full commercial use. No attribution requirement. No revenue threshold. No monthly active user ceiling. Weights: Hugging Face, available today. Runs on: vLLM, Ollama, SGLang, and any standard GGUF-compatible inference engine. Qwen 4 32B also runs at approximately 135 tokens per second on an M5 Max chip, setting a new bar for what a sub-8GB model can do on Apple Silicon. The open-source coding model just beat the best closed-source model in the world on the benchmark designed to test whether AI can actually do software engineering. The weights are free. The subscription is optional. Source: Autom8Labs AI Insight July 2026, State of Open Source LLMs June 2026, Kunal Ganglani blog June 2026.

41,278 views • 1 month ago

Every project management tool was designed by project managers, for project managers. This one was designed for ADHD, dyslexic, and autistic brains instead. And it turns out that also makes it better for literally everyone who just wants to get work done without configuring a tool for two weeks first. It’s called Leantime. Most PM tools throw you straight into a task board and expect you to already know what a “sprint” is. Leantime is built around a different idea: tasks should trace back to a goal, not float in a backlog with no reason attached. → Ships with strategic planning tools, Lean Canvas, SWOT analysis, built to connect the “why” to the actual task list, not just a bare Kanban board → The same tasks render as Kanban, table, or list, whichever your brain processes better on a given day → Gantt-style milestone timeline, a built-in project wiki, and time tracking, all native, not four separate tools stitched together → Interface is deliberately built to reduce cognitive overload and context-switching, an actual design principle here, not an accessibility checkbox added later → Self-host via Docker in under an hour, your team’s entire project history stays on a server you control Jira was built assuming a certified project manager runs the workflow. Most teams are five people trying to ship something, not an enterprise PMO. Leantime is what a PM tool looks like when it’s built for the second group. Open source. AGPL-3.0. 10,000+ GitHub stars.

Every project management tool was designed by project managers, for project managers. This one was designed for ADHD, dyslexic, and autistic brains instead. And it turns out that also makes it better for literally everyone who just wants to get work done without configuring a tool for two weeks first. It’s called Leantime. Most PM tools throw you straight into a task board and expect you to already know what a “sprint” is. Leantime is built around a different idea: tasks should trace back to a goal, not float in a backlog with no reason attached. → Ships with strategic planning tools, Lean Canvas, SWOT analysis, built to connect the “why” to the actual task list, not just a bare Kanban board → The same tasks render as Kanban, table, or list, whichever your brain processes better on a given day → Gantt-style milestone timeline, a built-in project wiki, and time tracking, all native, not four separate tools stitched together → Interface is deliberately built to reduce cognitive overload and context-switching, an actual design principle here, not an accessibility checkbox added later → Self-host via Docker in under an hour, your team’s entire project history stays on a server you control Jira was built assuming a certified project manager runs the workflow. Most teams are five people trying to ship something, not an enterprise PMO. Leantime is what a PM tool looks like when it’s built for the second group. Open source. AGPL-3.0. 10,000+ GitHub stars.

31,134 views • 1 month ago

Toyota had a single access key sitting in a public GitHub repo. Nobody caught it for years. By the time it was found in 2022, customer data belonging to hundreds of thousands of people had been exposed the entire time. That’s not a hypothetical. That’s one hardcoded secret, forgotten in a repo, doing quiet damage for years. It’s called Infisical, and it exists because “just put it in a .env file” is how almost every credential leak starts. → Centralizes every API key, secret, and cert across dev, staging, and prod, with full versioning and point-in-time rollback → Scans 140+ secret types across your files, directories, and entire git history, the same kind of scanning that catches leaks like Toyota’s before they sit exposed for years → Agent Vault brokers your AI agents’ access to external APIs: the agent only ever sees a placeholder, the real secret gets injected at a proxy layer it never touches, so a prompt-injected agent can’t leak what it was never given → Honey tokens plant decoy credentials next to your real ones, so the second an attacker touches a fake key, your team gets an alert instead of a breach report → Full audit trail on every credential your team and your AI tools use, plus a private PKI to issue and manage certificates without a third-party CA GitGuardian tracked over 28 million new secrets leaked on public GitHub in 2025 alone. Most companies still find out the same way Toyota did: too late, by accident, years after the fact. MIT License (core). 12,700+ GitHub stars. Self-host free, unlimited users.

Toyota had a single access key sitting in a public GitHub repo. Nobody caught it for years. By the time it was found in 2022, customer data belonging to hundreds of thousands of people had been exposed the entire time. That’s not a hypothetical. That’s one hardcoded secret, forgotten in a repo, doing quiet damage for years. It’s called Infisical, and it exists because “just put it in a .env file” is how almost every credential leak starts. → Centralizes every API key, secret, and cert across dev, staging, and prod, with full versioning and point-in-time rollback → Scans 140+ secret types across your files, directories, and entire git history, the same kind of scanning that catches leaks like Toyota’s before they sit exposed for years → Agent Vault brokers your AI agents’ access to external APIs: the agent only ever sees a placeholder, the real secret gets injected at a proxy layer it never touches, so a prompt-injected agent can’t leak what it was never given → Honey tokens plant decoy credentials next to your real ones, so the second an attacker touches a fake key, your team gets an alert instead of a breach report → Full audit trail on every credential your team and your AI tools use, plus a private PKI to issue and manage certificates without a third-party CA GitGuardian tracked over 28 million new secrets leaked on public GitHub in 2025 alone. Most companies still find out the same way Toyota did: too late, by accident, years after the fact. MIT License (core). 12,700+ GitHub stars. Self-host free, unlimited users.

29,372 views • 1 month ago

No more content to load