freshcrate — Search

Procedural memory for AI coding agents: transforms scattered session history into persistent, cross-agent memory so every agent learns from every other

ai-agents bun developer-tools memory typescriptby DicklesworthstoneTypeScript

SeekStorm 📁v3.0.0🌳 Mature⭐1,865

SeekStorm: vector & lexical search - in-process library & multi-tenancy server, in Rust.

ai-search bm25 dense-retrieval enterprise-search faceting full-text-search geosearch hybrid-search rust vector-databaseby SeekStormRust

agentic-memory 📁0.0.0🌿 Growing⭐179

No description

by lhl

kotlinx-schema 📁v0.5.0🌿 Growing⭐115

Kotlin Multiplatform library that generates JSON Schemas from your methods and classes both at compile-time via Kotlin Symbol Processing(KSP) and at runtime via reflection or kotlinx.serialization.

code-generation json-schema kotlin kotlin-symbol-processing kotlin-symbol-processorby KotlinKotlin

python-sdk 📁v1.27.0🏛️ Flagship⭐22,712

The official Python SDK for Model Context Protocol servers and clients

pythonby modelcontextprotocolPython

txtai 📁v9.7.0🏛️ Flagship⭐12,412

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

agents ai ai-agents embeddings information-retrieval language-model large-language-models llm python vector-databaseby neumlPython

outlines 📁1.2.12🏛️ Flagship⭐13,705

Structured Outputs

cfg generative-ai json llms prompt-engineering python regex structured-generation symbolic-aiby dottxt-aiPython

cortexdb 📁v2.18.1🌱 Seedling⭐32

A lightweight, embeddable vector database library for Go AI projects.

embeddings go hindsight llm rag sqlite vector-database vector-searchby liliang-cnGo

ToolAgents 📁0.3.0🌱 Seedling⭐35

ToolAgents is a lightweight and flexible framework for creating function-calling agents with various language models and APIs.

agent agents function-calling llm llm-agent llm-agents llms local-llm pythonby Maximilian-WinterPython

OpenClawProBench 📁main@2026-04-15🌿 Growing⭐453

OpenClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

agent benchmark evaluation harness leaderboard llm openclaw pythonby suyoumoPython

llm-gateway 📁v0.1.4🌿 Growing⭐55

Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load balancing across OpenAI, Anthropic, Ollama, vLLM, and any compatible backend. Identity-based access, virtual A

agentic-ai ai-gateway ai-infrastructure ai-security anthropic e2e-encryption go llm-gateway llm-proxyby openzitiGo

Nreki 📁v10.5.1🌱 Seedling⭐10

MCP plugin that intercepts AI agent edits in RAM, validates them (TypeScript compiler + gopls + pyright), auto-heals missing imports, and commits atomically. If anything breaks, disk stays untouched

acid-transactions ai-code-review ai-safety auto-healing claude-code code-safety gopls lsp mcp typescriptby Ruso-0TypeScript

swaggie 📁v2.1.1🌱 Seedling⭐25

Tool for generating TypeScript client code for given Swagger API endpoints

code-generation code-generators codegen nswag openapi openapi3 openapi30 openapi31 typescriptby yhnaveinTypeScript

dlite 📁v0.5.40🌱 Seedling⭐43

DLite - a lightweight data-centric framework for semantic interoperability

c code-generation interoperability metadata semantic-interoperabilityby SINTEFC

coherent-design-method 📁v0.7.15🌱 Seedling⭐4

AI-powered design system generator — once designed, consistent UI everywhere.

ai cli code-generation code-generator design-system design-systems nextjs react typescriptby skovtunTypeScript

summoner-agents 📁v1.1.0🌱 Seedling⭐24

A collection of Summoner clients and agents featuring example implementations and reusable templates