Remnic
PulseGate's liveness check found it on 8 Oct 2026; it is registered on GitHub and has been in the index since 19 Aug 2026. How this is checked
Remnic is an open-source, local-first memory store that lets AI agents share context across sessions and tools. It stores memories as plain Markdown files on the user's machine, with recall and extraction workflows for Claude Code, Codex CLI, Cursor, ChatGPT, and MCP clients.
Inferred · not functionally tested
Overview
6 featuresPurpose: Preventing AI agents from losing project context, decisions, and user preferences between sessions.
Inferred · not functionally tested
Audience: developers using AI coding agents
Inferred · not functionally tested
Functions: agents
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: MIT · platforms: API, CLI, WEB · deployment: browser, cli, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: remnic.ai · github.com. These links do not verify the individual claims.
In the Memory & skills space, Remnic takes a focused approach. Inferred · not functionally tested: It focuses on preventing AI agents from losing project context, decisions, and user preferences between sessions. Inferred · not functionally tested: Remnic is an open-source project aimed at developers using AI coding agents. Basis unknown · not verified: Remnic is open source under the MIT license. Basis unknown · not verified: Remnic is available on the web and the command line, and it can be self-hosted.
Joshua S. Warren builds and maintains Remnic, and it first shipped in 2026. The project is developed in the open on GitHub with 170 stars and 2.4k commits in the last 90 days. Inferred · not functionally tested: Key capabilities include shared agent memory, markdown storage, and memory recall. Inferred · not functionally tested: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Shared agent memory
- Markdown storage
- Memory recall
- Post-turn extraction
- Memory provenance
- Correction controls
Topics: Inferred · not functionally tested
Built with & integrations
- Astro
- /_astro/ in the HTML
- local_oss
- bollama in the HTML · bvllm in the HTML · studio in the HTML
- Cloudflare
- cf-ray header · cf-cache-status header
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed19 Aug · 15:14 UTCjoshuaswarren/remnic seen via GitHub Search (Smart)Source: GitHub Search (Smart) · Open
Frequently asked questions about Remnic
- What is Remnic?
- Inferred · not functionally tested: Remnic focuses on preventing AI agents from losing project context, decisions, and user preferences between sessions. It is catalogued under Memory & skills on PulseGate.
- Who should use Remnic?
- Inferred · not functionally tested: Remnic is an open-source project built for developers using AI coding agents.
- Does Remnic have a free plan?
- Basis unknown · not verified: Yes — Remnic is open source under the MIT license and free to use.
- What platforms does Remnic run on?
- Basis unknown · not verified: Remnic runs on the web and the command line. It can also be self-hosted.
- Is Remnic still active?
- PulseGate's liveness check found it on 8 Oct 2026. Its GitHub repository shows 2.4k commits in the last 90 days.
- What are alternatives to Remnic?
- Similar projects tracked by PulseGate include Memnest, remem, and rememori.Memnestrememrememori
- Who makes Remnic?
- Remnic is developed by Joshua S. Warren.
- How long has Remnic been around?
- Remnic first shipped in 2026.
Similar projects
Closest matches by what these projects do