agentleFS changelog

version

0.12.17 → 0.12.21

version

0.12.16 → 0.12.17

version

0.12.12 → 0.12.16

version

0.12.11 → 0.12.12

version

0.12.10 → 0.12.11

version

0.12.8 → 0.12.10

https://agentlefs.com/llms.txt

− Shared second brain for any AI with agent permissions. One folder Claude Code, Cursor and Codex all read, where an agent reads only what its person can, every write is a version, and a folder can be shared outside your company.− - [Agent permissions for files your team shares — agentleFS](https://agentlefs.com/): One folder Claude Code, Cursor and Codex all read over MCP. An agent reads only what its person can, every write is a version, and folders share outward.− - [Connect Claude or Cursor over MCP — agentleFS](https://agentlefs.com/docs/connect): Add agentleFS to Claude Code, Claude Desktop, Cursor or any MCP client. You sign in through the browser, and the agent reads what you are allowed to read.+ Shared second brain for any AI with agent permissions. Teammates choose their models, providers and harnesses while sharing context, work and the reasoning behind decisions. Each agent works within the access it receives.+ - [Team and AI agent collaboration — agentleFS](https://agentlefs.com/): Shared context, decisions and work across models, providers and harnesses. Let teammates choose their AI tools and collaborate from one permissioned workspace.+ - [Collaboration across agents and AI tools — agentleFS](https://agentlefs.com/solutions): Coordinate people and agents with shared documents, claims, handoffs and durable waits. Explore shared knowledge, decision history, skills and access controls.+ - [Coordinate your team’s agents — agentleFS](https://agentlefs.com/solutions/collaboration): Compare approaches in a team ballot, prepare a work brief, and coordinate agents with claims, handoffs, durable waits and progress reports.+ - [Shared knowledge for every AI — agentleFS](https://agentlefs.com/solutions/knowledge): Bring project notes, linked documents, GitHub and Drive sources, and shared skills into one place your team’s agents can work from.+ - [Agent access and sharing — agentleFS](https://agentlefs.com/solutions/access): Choose roles on folders and files, narrow each agent’s delegated scope, and review access without handing over your whole workspace.+ - [Karpathy is wrong: the agent is the tape | agentleFS](https://agentlefs.com/blog/the-agent-is-the-tape): An agent should be the context it carries, like a Turing machine's tape, and the model only the head that reads it, so any lab's model can take the seat.+ - [Agent swarms and the CI bottleneck | agentleFS](https://agentlefs.com/blog/two-way-messaging-for-agent-swarms): With more coding agents, CI is the new bottleneck. Agents that coordinate in shared documents landed 25 fixes on 4 full CI runs, each passing the first time.+ - [Meta harness: async agent collaboration | agentleFS](https://agentlefs.com/blog/meta-harness-async-agent-collaboration): Our coming meta harness connects agent sessions with a shared UX, async callbacks and permissioned cross-harness work. Read the approach and join the waitlist.+ - [Agent swarm communication with shared docs | agentleFS](https://agentlefs.com/blog/agent-swarm-communication): Doorbell-and-cabinet swarms on agentleFS: coordinator–worker, shared docs, cron heads. How the wake works, what we measured, and a Product→Admin loop.+ - [Team ballots, handoffs and shared work — agentleFS](https://agentlefs.com/docs/collaboration): Choose an approach with a team ballot, then coordinate agents through shared documents, claims, handoffs, durable waits and execution reports.+ - [Connect your harness: plugin or MCP — agentleFS](https://agentlefs.com/docs/connect): Add agentleFS to Claude Code, Claude Desktop, Cursor or any MCP client. You sign in through the browser, and the agent reads what you are allowed to read.

version

0.12.7 → 0.12.8

version

0.8.0 → 0.12.7

version

0.7.11 → 0.8.0

version

0.7.9 → 0.7.11

version

0.7.8 → 0.7.9

version

0.7.6 → 0.7.8

version

0.7.2 → 0.7.6

version

0.7.1 → 0.7.2

version

0.6.2 → 0.7.1

https://agentlefs.com/llms.txt

− The full FAQ is inline at [llms-full.txt](https://agentlefs.com/llms-full.txt), 51 entries+ - [How-to guides for agent memory and context | agentleFS](https://agentlefs.com/blog/how-to): Step-by-step guides to agent memory and context: writing CLAUDE.md and AGENTS.md files, checking them, and the rules worth enforcing with hooks.+ - [Private AI: keep your competitive advantage | agentleFS](https://agentlefs.com/blog/private-ai-local-llm): Is ChatGPT safe for confidential information? Private AI needs private data and private inference. Here's how to get both, with a local LLM.+ - [ChatGPT to Claude, and back, without losing work | agentleFS](https://agentlefs.com/blog/chatgpt-to-claude): Switch between ChatGPT, Claude and Gemini without copying and pasting: connect every AI to one agentleFS folder, and each one reads the same plans.+ - [Claude Code agent teams that share files safely | agentleFS](https://agentlefs.com/blog/claude-code-agent-teams): Claude Code subagents inherit your MCP tools and permission mode. Give each one its own agentleFS identity, scoped to one folder and ended with one call.+ - [Claude Code memory: your personal CLAUDE.md | agentleFS](https://agentlefs.com/blog/claude-code-memory): Your personal CLAUDE.md lives on one laptop and your team's lives in the repo. Keep yours where every AI reads it, on every machine, outside the repo.+ - [CLAUDE.md and AGENTS.md examples from real repos | agentleFS](https://agentlefs.com/blog/claude-md-examples): Twelve real CLAUDE.md and AGENTS.md examples from well-starred repos, the lines worth copying, and a short template. The good ones are short.+ - [Claude skills in every AI, shared with your team | agentleFS](https://agentlefs.com/blog/claude-skills): Claude skills live on one disk or in one repo. Keep them in one agentleFS folder that Claude, Codex, Gemini and Grok all read, and share it with your team.+ - [Obsidian + Claude: a second brain every AI reads | agentleFS](https://agentlefs.com/blog/obsidian-claude-second-brain): Obsidian keeps your vault on your own devices, where no AI can read Sync's copies. Put it in agentleFS, and Claude, ChatGPT and Gemini read it anywhere.+ - [Share a Claude project with anyone, and their AI | agentleFS](https://agentlefs.com/blog/share-claude-project): Claude shares a project only inside one Team or Enterprise org. Here's how to share one with anyone, and let each person's own AI read and write it.+ The full FAQ is inline at [llms-full.txt](https://agentlefs.com/llms-full.txt), 57 entries

version

0.5.12 → 0.6.2

version

0.5.10 → 0.5.12

version

0.5.9 → 0.5.10

version

0.5.8 → 0.5.9

https://agentlefs.com/llms.txt

− Agent permissions for the files your team shares. One folder Claude Code, Cursor and Codex all read, where an agent reads only what its person can, every write is a version, and a folder can be shared outside your company.+ Shared second brain for any AI with agent permissions. One folder Claude Code, Cursor and Codex all read, where an agent reads only what its person can, every write is a version, and a folder can be shared outside your company.+ - [Blog: Agent memory and agent context | agentleFS](https://agentlefs.com/blog): Engineering persistent agent memory and useful agent context: retrieval, lifecycle hooks, shared knowledge, and lessons from real instruction files.+ - [Persistent AI Agent Memory: MCP and Hooks | agentleFS](https://agentlefs.com/blog/persistent-ai-agent-memory-lifecycle-hooks): How persistent AI agent memory moves from optional MCP calls to lifecycle hooks, with retrieval deadlines, durable capture, and honest failure policies.+ - [External Agent Memory Across Clients | agentleFS](https://agentlefs.com/blog/agent-memory-outside-the-harness): Why external agent memory enables cross-client continuity, deliberate sharing across tenants, and a retrieval stack you can tune and evaluate.+ - [CLAUDE.md best practices from 5,786 real files — agentleFS](https://agentlefs.com/blog/claude-md-best-practices): CLAUDE.md and AGENTS.md best practices from 5,786 real files: what people cut as models improved, what they kept, and what to enforce with hooks.

version

0.5.6 → 0.5.8

description

Agent permissions for the files your team shares → Shared second brain for any AI with agent permissions

version

0.5.4 → 0.5.6

version

0.4.7 → 0.5.4

version

0.4.3 → 0.4.7

https://agentlefs.com/llms.txt

− The full FAQ is inline at [llms-full.txt](https://agentlefs.com/llms-full.txt), 46 entries+ The full FAQ is inline at [llms-full.txt](https://agentlefs.com/llms-full.txt), 51 entries

version

0.4.1 → 0.4.3

version

0.3.7 → 0.4.1

version

0.3.6 → 0.3.7

version

0.3.1 → 0.3.6