for anyone switching, moving over, or just getting started with claude we have the most up to date and comprehensive repository to maximize your agent harness potential maintained by me and the community everything is succinctly explained in more detail in the guides below
▶@ctatedev
@LiorOnAI
▶@coreyhainesco
▶@abouelatta_ali
▶@NousResearch
@Fried_rice
@dhruvtwt_
▶@DataChazTechniques I'd master if building RAG systems that actually work:
Bookmark this.
1. Sliding Window Chunking
2. Semantic Chunking
3. Document Hierarchies
4. Metadata Enrichment
5. Query Expansion
6. Hybrid Search
7. Reranking Models
8. Context Window Packing
9. Lost in the Middle Problem
10. Hypothetical Document Embeddings (HyDE)
11. Multi-Query Retrieval
12. Contextual Compression
13. Sentence Window Retrieval
14. Auto-Merging Retrieval
15. Cross-Encoder Rescoring
16. Temporal Context Decay
17. Negative Sampling
18. MMR (Maximal Marginal Relevance)
19. Graph-Based Retrieval
20. Recursive Retrieval
21. Citation Trackingchunks
22. Context Ablation Testing
23. Adaptive Retrieval@athleticKoder
▶@CopilotKit
▶@whosjunaiddthe fact that http://pi.dev agent is so good, with virtually no sophisticated harness whatsoever, is a testament to the fact token vendor (codex/claude) agents are overrated. highly.
today's moat of codex/claude tools is GIVING TOKENS FOR FREE LEFT AND RIGHT to make you dependant@krzyzanowskimIntroducing eve, an agent framework.
𝚊𝚐𝚎𝚗𝚝/
𝚊𝚐𝚎𝚗𝚝.𝚝𝚜
𝚒𝚗𝚜𝚝𝚛𝚞𝚌𝚝𝚒𝚘𝚗𝚜.𝚖𝚍
𝚝𝚘𝚘𝚕𝚜/
𝚜𝚔𝚒𝚕𝚕𝚜/
𝚜𝚊𝚗𝚍𝚋𝚘𝚡/
𝚜𝚌𝚑𝚎𝚍𝚞𝚕𝚎𝚜/
Like Next.js, for agents.
https://vercel.com/blog/introducing-eve@vercelVercel Ship (so far)
▲ Vercel Services
— Run full stack on Vercel
— Microservices on Vercel
— Private service comms
▲ eve
— The framework for building agents
— Durable agents with one folder
— Sandboxing, approvals and evals
▲ WebSocket support
— Persistent connections
▲ Vercel Functions
— Dockerfile support
— 5 GB packages, 30 min
— Zero-config Node servers
▲ Vercel Agent in Dashboard
— Autonomous investigations
— Plan-based permissions
— Fixes surfaced as PRs
▲ Vercel Container Registry
— Container images on Vercel
— OCI push, pull and tag
▲ Vercel Sandbox
— Custom images
— Persistent sandbox storage
— 24 hour runtime + expiration
▲ AI SDK 7 + agent harnesses
— Toolkit for building agents
— Coding-agent harnesses
▲ Chat SDK
— Multi-channel agents
▲ Access & security
— Vercel Passport: OIDC access
— Vercel Connect: external services
— OIDC audiences + Audit Logs
▲ Enterprise apps and agents
— Security posture dashboard
— Vercel Functions in your cloud
▲ AI Gateway
— Voice, speech and transcription
— API key budgets
▲ Vercel Blob
— Private blob storage
— Signed URLs and OIDC auth
▲ Builds & deployments
— 500 concurrent builds for Pro
— Vercel Drop
— Elastic builds
▲ Vercel CLI
— Speed Insights + Web Analytics
— Trace any request
— Deployment limits removed
▲ Observability
— Trace eve sessions
— Trace Workflow runs
▲ Workflows
— Inflight cancellation
— Nitro v3 + TanStack Start
▲ SDK-free Vercel Flags
— No SDK keys@ctatedevA single place to browse, compare, and install Clawdbot skills by intent.
Built for fast discovery and practical use.
GitHub Repository:
https://github.com/VoltAgent/awesome-clawdbot-skills@GithubProjects
▶@dr_cintas
▶@askalphaxiv
@matsugfxAnnouncing Paper Desktop + MCP
Now any agent can read or write with Paper
Paper is connected. To your code. To your agents. To your data. To your teammates.
Download Paper Desktop at http://paper.design@paper
▶@hyperbrowser
@xmayeth+1
▶@TheAhmadOsman
@om_patel5I took the @karpathy autoresearch loop and pointed it at markets.
25 AI agents debate macro, rates, commodities, sectors, and single stocks daily. Every recommendation scored against real outcomes. Worst agent by rolling Sharpe gets its prompt rewritten by the system. Keep or revert. Same loop, prompts are the weights, Sharpe is the loss function.
Trained the agents on 18 months of market data. 378 iterations. 54 prompt modifications, 16 survived.
The system learned which agents to trust using Darwinian weights — geopolitical, commodities, and the @BillAckman quality compounder rose to the top.
The agents even figured out their own portfolio manager was the weakest link before we did!
Deployed the trained agents. +22% in 173 days. Best pick: AVGO at $152, held for +128%.
The final prompts are evolutionary products — shaped by market feedback, not human intuition. Now running live with my own capital.
https://github.com/chrisworsey55/atlas-gic
Part hedge fund, part research experiment :)@Chris_WorseyThis is a Claude Code Skill, a refined security knowledge base based on 88,636 real vulnerability cases collected by WooYun from 2010 to 2016.
After installing this Skill, Claude can think about vulnerability issues like a senior security expert. #AiSecurity
https://github.com/tanweai/wooyun-legacy@blackorbird
@everyTop 5 local LLMs:
1. GLM-4.5-air: best agentic/coding model that runs on consumer hardware at very decent speeds. Rivals Claude 4-sonnet.
2. Nousresearch/hermes-70B: the only model that will do whatever you ask, and tell you whatever you want to know. Literally critical to have.
3. GPT-OSS-120B: very intelligent it’s like having 4o at home, great context window, great agent
4. Qwen3-coder-30B-3A-instruct: very good coding agent, excellent workhorse, incredibly fast
5. Mistral-magistral-small: very fast, excellent agent, great coder, multimodal, punches way, way, above its size.
I would be okay never using a proprietary llm, although given the subsidised compute I will continue to use them since I’m getting free leverage.@0xSeroI've tried all ( 74 😵💫 ) AI Coding Agents & IDEs
[Rork, CodeRabbit, Anima, Zed, Factory, Cursor, Windsurf, Copilot, Lovable, Bolt, v0, Replit, MarsX, Canva, Devin, Github Spark, Vercel, Lindy, Warp, Figma, Cline, Vibe Coder & more]
The most complete list ever made (with demos & notes):@johnrushx
@realmcore_Check it out:
https://ai-sdk.dev/docs/agents@nicoalbanese10