{"id":36236860,"url":"https://github.com/rawcontext/reflex","last_synced_at":"2026-01-11T06:01:56.708Z","repository":{"id":331245718,"uuid":"1124401170","full_name":"rawcontext/reflex","owner":"rawcontext","description":"Episodic memory and semantic cache proxy for LLM APIs with ~40% token savings","archived":false,"fork":false,"pushed_at":"2025-12-29T01:47:20.000Z","size":242,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-01-04T23:17:34.030Z","etag":null,"topics":["agent-orchestration","ai-agents","context-graph","developer-tools","knowledge-graph","llm-proxy","semantic-cache","token-optimization"],"latest_commit_sha":null,"homepage":"https://rawcontext.com/projects/reflex/","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rawcontext.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-29T00:43:20.000Z","updated_at":"2025-12-29T06:13:00.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/rawcontext/reflex","commit_stats":null,"previous_names":["rawcontext/reflex"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/rawcontext/reflex","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rawcontext%2Freflex","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rawcontext%2Freflex/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rawcontext%2Freflex/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rawcontext%2Freflex/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rawcontext","download_url":"https://codeload.github.com/rawcontext/reflex/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rawcontext%2Freflex/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28293188,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-11T04:44:51.577Z","status":"ssl_error","status_checked_at":"2026-01-11T04:44:44.232Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-orchestration","ai-agents","context-graph","developer-tools","knowledge-graph","llm-proxy","semantic-cache","token-optimization"],"created_at":"2026-01-11T06:01:56.090Z","updated_at":"2026-01-11T06:01:56.700Z","avatar_url":"https://github.com/rawcontext.png","language":"Rust","readme":"\u003e **Under Construction**: This project is actively being developed and is not yet ready for production use. APIs and features may change without notice.\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eEpisodic Memory \u0026 Semantic Cache for LLM Responses\u003c/strong\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/rawcontext/reflex/actions\"\u003e\u003cimg src=\"https://img.shields.io/github/actions/workflow/status/rawcontext/reflex/ci.yml?branch=master\u0026style=flat-square\" alt=\"Build Status\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/rawcontext/reflex/blob/master/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/license-AGPL--3.0-blue?style=flat-square\" alt=\"License\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://crates.io/crates/reflex-cache\"\u003e\u003cimg src=\"https://img.shields.io/crates/v/reflex-cache?style=flat-square\" alt=\"Crates.io\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/rawcontext/reflex\"\u003e\u003cimg src=\"https://img.shields.io/badge/rust-2024_edition-orange?style=flat-square\" alt=\"Rust 2024\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cem\u003eBecause nobody likes paying for the same token twice.\u003c/em\u003e\n\u003c/p\u003e\n\n\u003cp\u003e\n  \u003cpre align=\"center\"\u003e\n██████╗ ███████╗███████╗██╗     ███████╗██╗  ██╗\n██╔══██╗██╔════╝██╔════╝██║     ██╔════╝╚██╗██╔╝\n██████╔╝█████╗  █████╗  ██║     █████╗   ╚███╔╝\n██╔══██╗██╔══╝  ██╔══╝  ██║     ██╔══╝   ██╔██╗\n██║  ██║███████╗██║     ███████╗███████╗██╔╝ ██╗\n╚═╝  ╚═╝╚══════╝╚═╝     ╚══════╝╚══════╝╚═╝  ╚═╝\n  \u003c/pre\u003e\n\u003c/p\u003e\n\n---\n\n## What It Is\n\nReflex is an **OpenAI-compatible HTTP cache** for LLM responses: it sits between your agent/app and the provider, returning cached answers instantly and storing misses for later reuse. Cached responses are returned in [Tauq](https://github.com/epistates/tauq) format to reduce token overhead.\n\n---\n\n## Quick Start (Server)\n\n```bash\n# 1. Start Qdrant (vector database)\ndocker run -d -p 6334:6334 -p 6333:6333 qdrant/qdrant\n\n# 2. Run Reflex (HTTP server)\ncargo run -p reflex-server --release\n\n# 3. Point your agent to localhost:8080\nexport OPENAI_BASE_URL=http://localhost:8080/v1\n```\n\n---\n\n## Quick Start (Library)\n\n```bash\n# Run the library example (no HTTP server)\ncargo run -p reflex-cache --example basic_lookup --features mock\n```\n\nEmbed in your own app:\n\n```toml\n[dependencies]\nreflex = { package = \"reflex-cache\", version = \"x.x.x\" }\n```\n\n---\n\n## Crates In This Repo\n\n- **Server + binary (`reflex`)**: [crates/reflex-server](crates/reflex-server/README.md)\n- **Core library (embedded use)**: [crates/reflex-cache](crates/reflex-cache/README.md) (docs.rs: https://docs.rs/reflex-cache)\n\n---\n\n## How It Works (High Level)\n\n```\nRequest → L1 (exact) → L2 (semantic) → L3 (rerank/verify) → Provider\n```\n\n- **L1**: exact match (fast, in-memory)\n- **L2**: semantic retrieval (Qdrant vector search)\n- **L3**: verification (cross-encoder rerank to avoid false positives)\n\n---\n\n## Development\n\n```bash\ncargo test\ncargo clippy --all-targets -- -D warnings\ncargo fmt -- --check\n```\n\n---\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eReflex: Stop paying for the same token twice.\u003c/strong\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003csub\u003eBuilt with Rust, Qdrant, and a healthy disdain for redundant API calls.\u003c/sub\u003e\n\u003c/p\u003e\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frawcontext%2Freflex","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frawcontext%2Freflex","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frawcontext%2Freflex/lists"}