Radar / AI infrastructure / ai-memory
ai-memory - git-backed long-term memory shared across coding agents
Rust server and CLI that captures agent sessions via lifecycle hooks, compiles them into a git-backed markdown wiki, and hands the next agent a bounded brief plus typed one-claim handoffs - zero LLM calls by default.
Why it matters
Memory as an inspectable markdown wiki in git instead of a black-box vector store, shared across agents, machines, and people; #5 on GitHub daily trending on Oct 18 with ~10k stars.
What you could build with it
A two-person startup could share one git-backed memory wiki across Claude Code and Codex so handoffs between engineers and agents stop losing project context.
Does it hold up?
Usable today for self-hosters bouncing between Claude Code and Codex - a real VPS deployment works in daily use and a community test campaign ran hundreds of scenarios with perfect recall numbers. Caveats: young and fast-moving (v3.1.0, Oct 16 2026), and hooks capture prompts, so secrets hygiene matters before pointing it at sensitive repos.
Built with ai-memory
- AI-memory on VPSdev.to · Real user deployment writeup: runs ai-memory centralized on a cheap 1-core VPS via an Ansible setup (SSH key, reverse proxy, TLS cert), so memory follows the author across machines; reports it working in daily use across environments.
- ai-memory A2A v0.6.3.1 campaignalphaonedev.github.io · Community-run test campaign wiring real agents (IronClaw, Hermes, OpenClaw) across a 4-node mesh through ai-memory's MCP interface: 315/315 scenarios green, recall@1 of 1.0 over 52 pre-seeded memories, plus an honest negative - agents confabulated instead of recalling without an explicit prompt cue.
- alphaonedev/ai-memory-a2a-v0.6.3.1github · Per-release certification harness validating what happens when real heterogeneous AI agents use ai-memory to communicate - scripted cross-agent write, recall, and handoff scenarios with published JSON evidence.
Learn more
First spotted on github: source.
More AI infrastructure
DeepGEMM: DeepSeek's open GPU BLAS kernel libraryDeepSeek's DeepGEMM, a clean and efficient open-source BLAS kernel library for NVIDIA GPUs (up to 1550 TFLOPS on…infra · JEV 0.77OpenViking — self-evolving context database for AI agentsByteDance Volcengine's open-source (AGPL-3.0) context database that unifies agent memory, knowledge RAG, and skills…infra · JEV 0.76Modular open-sources MAX inference server, Mojo stdlib and accelerator kernelsThe core of Modular's unified AI deployment stack is now open: the MAX inference server (OpenAI-compatible endpoints)…infra · JEV 0.76OmniRouteFree MIT AI gateway: one endpoint, 290+ providers and 500+ models with quota-aware auto-fallback.infra · JEV 0.75Context Mode: context-window optimization for AI coding agentsMCP server for AI coding agents that sandboxes verbose tool output and persists session memory, cutting context use by…infra · JEV 0.74StrataOpen-source inference engine that runs the 125B-parameter Qwen3.8-Flash-Next MoE on a single consumer GPU with 12GB+…infra · JEV 0.74
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.