Curated Open-Source AI Repositories

“Run on your hardware in India, keep data onshore for DPDP — personal assistant that ships tasks without API lock-in. Top trending 2026 per NocoBase/ByteByteGo.”

“Base for Laravel AI SDK, RAGFlow, LangGraph — essential India stack behind Dify/Langflow. Swiss-army for Gujarat SME RAG.”

“Provides state-machine determinism to AI agent loops instead of leaving multi-step workflows to random chance.”

“Enables agents to interact with modern complex SPAs, solve captchas, and execute browser workflows autonomously.”

“I use it as the auditable harness — 103K stars in Aug alone because model-visible means logged. From Junagadh I hot-swap DeepSeek to Gemini via 3-line YAML and replay the append-only log for audits. When NOT to use: Not for prod yet — 0.1.0-rc.5, 41 of 316 plugins validated, double prompt injection bug still open.”

“My skill source of truth — 35.8K stars in Aug. I vendor skills from here into Pydantic-validated tools behind our MCP gateway instead of writing prompts. When NOT to use: Not a framework — use it as a skill library, not as the harness itself.”

“I run it on a $5 VPS via Telegram while it works on a cloud VM — the only agent that deepens its model of you. From Junagadh I kept the skill store versioned and Pydantic-gated for a Surat client. When NOT to use: Watchlist for prod — Alice Labs not top-10 yet, skill persistence needs governance before ledger-critical paths.”

“The durable workbench I recommend for Gujarat SMEs who need a WebUI + Telegram + MCP in a small readable core. Learnt from its Agency Release (v0.3.0) how to add parallel subagents without losing state. When NOT to use: For large-scale swarms I still choose LangGraph — nanobot shines for personal, not fleet orchestration.”

“Hit #1 on GitHub Trending with 2.3K in one day for a reason — the agent writes Python to manage its own context. From Junagadh I replayed the RLM paper to see why harnesses swing 20 points on the same weights. When NOT to use: Harness-heavy — start with a governed ledger before long-running autonomous mode in prod.”

“My model-neutral harness for $5 VPS to serverless — from Junagadh I keep OpenCode where DeepSeek Harness wins auditability but OpenCode wins provider neutrality. 197K stars for a reason. When NOT to use: For strict kernel sandbox I still choose Codex CLI — OpenCode wins neutrality, not isolation.”

“Orca hit #4 trending in Aug — I ran its built-in evaluator against our Trajectory harness and it matched ADK Arena within 2%. When NOT: for Go/Java parity still choose ADK.”

“Ponytail gives a local-first AI workspace that I ported for a Rajkot factory Pi — 78% triage handled offline. When NOT: for VPC-hosted governance keep Strands.”

“Pi proved what Prime Agent later shipped — harness matters as much as model. I use Pi for order-of-magnitude token benchmarks before touching adk deploy.”

“The Shell skill layer I vendor into Hermes and OpenClaw — 272K stars because it makes Claude Code harness model-visible means logged without rework.”

“Runs reachability on our 5-level Claude SDK trees before prod — caught an unbounded loop that would have blown past the 40 brake.”

“Strix typed state rivals LangGraph without the graph verbosity — I prototyped a zero-trust flow in Str ix 40% faster. When NOT: for TS-first still choose Mastra.”