# resonant

> Open-source relational AI framework with identity persistence, memory, and MCP integration. Build relationship-aware AI agents that remember, grow, and maintain continuity. Built on Claude Agent SDK.

- **URL**: https://www.freshcrate.ai/projects/resonant
- **Author**: codependentai
- **Category**: MCP Servers
- **Latest version**: `v2.3.0` (2026-05-12)
- **License**: Apache-2.0
- **Source**: https://github.com/codependentai/resonant
- **Language**: TypeScript
- **GitHub**: 27 stars, 9 forks
- **Registry**: github
- **Tags**: `agent-sdk`, `ai-agent`, `ai-companion`, `ai-identity`, `ai-memory`, `anthropic`, `claude`, `claude-code`, `llm-agent`, `typescript`

## Description

Open-source relational AI framework with identity persistence, memory, and MCP integration. Build relationship-aware AI agents that remember, grow, and maintain continuity. Built on Claude Agent SDK.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v2.3.0` | 2026-05-12 | High | ## What's new  **Pick your Claude credential.** Settings → Preferences → Authentication now offers two options: the **Claude Code subscription** (default, no per-query cost) or your own **Anthropic API key** (per-token billing, required for API-only models like Sonnet 4.5). Switching is hot — no restart, built-in tools and MCP all work identically either way. Full guide in [docs/AUTH.md](https://github.com/codependentai/resonant/blob/main/docs/AUTH.md).  **Per-turn token usage tracking** when yo |
| `v2.2.3` | 2026-05-08 | High | ## Bug Fixes  - **Mobile white screen on HTTP LAN origins** — Helmet's CSP defaults included `upgrade-insecure-requests`, which forced SvelteKit's dynamic module imports to upgrade to HTTPS on phones hitting the LAN IP (e.g. `192.168.x.x`). Desktop dev escaped this because `localhost` is always a secure context; phones were not, so imports rejected with no TLS available, `kit.start()` never ran, and the SPA never mounted. Opted out of `upgradeInsecureRequests` in the CSP directives — all other h |
| `v2.2.1` | 2026-05-01 | High | ## Tool Runtime Patch  - Adds provider-neutral file tools: `file.stat`, `file.list`, `file.read`, `file.search`, `file.write`, and `file.edit`. - Adds guarded public `web.fetch` for HTTP/HTTPS page reading with SSRF protections. - Adds visible path/URL preflight in chat, so pasted local paths and public links are inspected before model runtime and shown as tool activity. - Fixes continuity for non-session runtimes by injecting bounded recent thread history for providers like OpenAI Codex.  ## Ve |
| `v2.1.1` | 2026-04-06 | High | Patch release focused on safety net and reliability. No new features — all internal infrastructure plus a couple of bug fixes that affect every self-hoster.  ## Bug Fixes  - **Health endpoint** — \`/api/health\` now reports actual WebSocket connection count instead of hardcoded 0  ## Reliability  - **Database transaction safety** — \`markMessagesRead\`, \`addReaction\`, and \`removeReaction\` now wrapped in transactions to prevent partial writes and lost updates under concurrency - **Node 25 sta |
| `v2.1.0` | 2026-04-01 | Medium | ## What's New  - **Scratchpad** — persistent notes/tasks/events scratch pad on the Command Center home page. Full stack: DB, REST API, MCP tool (`cc_scratchpad`), and frontend component. - **Skills/plugin loading** — companion agent now discovers and loads skills from `.claude/skills/` directory automatically. - **The Scribe** — periodic conversation digest agent. Runs every 30 minutes on Haiku, produces daily markdown summaries of conversation in `data/digests/`. Uses configured companion/user |
| `v2.0.0` | 2026-03-30 | Medium | Resonant v2 is a major evolution — from a chat companion into a full companion ecosystem with life management, an overhauled UI, and deeper agent integration.  ## What's New  ### Command Center (`/cc`) A built-in life management system your companion can access and manage from chat.  - **9 pages**: Dashboard, Planner, Care Tracker, Calendar, Cycle Tracker, Pet Care, Lists, Finances, Stats - **12 MCP tools**: Your companion manages tasks, events, care, pets, lists, expenses, and more — all from c |
| `v1.4.1` | 2026-03-25 | Medium | ## What's New  This release introduces **agent-directed autonomy** — a conceptual model where the agent manages its own scheduling, awareness, and escalation from inside the conversation. Most agent harnesses give scheduling tools to users. Resonant gives them to the agent.  ### Routines (dynamic, agent-created)  Your companion can now create its own scheduled routines at runtime:  ```bash sc routine create "evening journal" "0 22 * * *" --prompt "Reflect on the day" sc routine remove evening_jo |
| `v1.4.0` | 2026-03-24 | Medium | ## What's New  ### Session Tracking  The Claude Agent SDK creates a new session file per `query()` call, even when resuming — leaving thousands of orphan `.jsonl` files over time. Resonant now tracks these transitions properly.  - **`session_history` table** records every session transition per thread, building a chain: A → B → C - **`scripts/index-sessions.mjs`** reconstructs session lineage for existing installations — matches ~97% of orphans to their threads via content analysis and timestamp |
| `v1.3.0` | 2026-03-23 | Medium | ## Bug Fixes  - **#7** — Custom wake types now supported. The orchestrator `schedules` config can register new wake types (not just override defaults). Wake prompts and prompt loading are fully dynamic. - **#6** — Fixed Telegram health check false-positives causing infinite restart loop during quiet periods. The stale-polling heuristic has been removed; `getMe()` connectivity check is sufficient. - **#5** — Fixed canvas text disappearing during editing. Reactive effect no longer resets local sta |
| `v1.2.0` | 2026-03-21 | Low | ## What's New  ### Semantic Search  Search conversation history by **meaning**, not just keywords.  "That conversation where we discussed the architecture" finds relevant messages — even if those exact words were never used. Powered by a local ML model that runs entirely on your machine. No API calls, no data leaves your system.  **How it works:** - Uses `all-MiniLM-L6-v2` (~30MB model, downloads once on first use) - New messages are embedded automatically - Backfill existing history with `sc ba |

## Citation

- HTML: https://www.freshcrate.ai/projects/resonant
- Markdown: https://www.freshcrate.ai/projects/resonant.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/resonant/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._