{"data":{"slug":"dcostenco-prism-coder","name":"prism-coder","tagline":"Persistent memory + local AI for coding agents.","github_url":"https://github.com/dcostenco/prism-coder","owner":"dcostenco","repo":"prism-coder","owner_avatar_url":"https://avatars.githubusercontent.com/u/64438937?v=4","primary_language":"TypeScript","stars":157,"forks":26,"topics":["agent-memory","ai-agent","claude-code","codex","cognitive-architecture","drift-detection","local-first","local-llm","mcp","mcp-server","memory","model-context-protocol","ollama","prism-coder","semantic-search","session-memory","sqlite","typescript","vector-search"],"archived":false,"github_pushed_at":"2026-09-20T04:10:17+00:00","maintenance_label":"Very active","stars_delta_30d":2,"url":"https://www.graphcanon.com/tools/dcostenco-prism-coder","markdown_url":"https://www.graphcanon.com/tools/dcostenco-prism-coder.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/dcostenco-prism-coder","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=dcostenco-prism-coder","description":"Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.","homepage_url":"https://synalux.ai/prism-mcp","license":"Apache-2.0","open_issues":1,"watchers":2,"ai_summary":"A platform that integrates persistent memory and local AI capabilities for coding assistance. Supports various code editors including VS Code, offering features such as offline operation, HIPAA compliance, and multi-agent coordination.","readme_excerpt":"### Install as a plugin\n\nPrism also ships as a plugin, which registers the MCP server and the startup\nskill for you.\n\nBoth hosts install straight from this repository. There is nothing to host and\nno server to run: the catalogue is the `.claude-plugin/marketplace.json` file\ncommitted here, and your client clones it from GitHub.\n\n**Claude Code:**\n\n```bash\nclaude plugin marketplace add dcostenco/prism-coder\nclaude plugin install prism-coder@prism\n```\n\n**Codex:**\n\n```bash\ncodex plugin marketplace add dcostenco/prism-coder\ncodex plugin add prism-coder@prism\n```\n\nThe plugin registers `prism-mcp` via `npx -y prism-mcp-server`. If you already\nconfigured Prism by hand — `prism connect` writes an `mcp_servers.prism-mcp`\nentry — you have that server twice under one key. Install the plugin **or**\nrun `prism connect`, not both.\n\n---\n\n### Subscription-Tier Skills Arrive Before the First Host Launch\n`prism connect` now downloads the authoritative Synalux skill manifest and\nmaterializes entitled packages in the native `~/.agents/skills` directory\nbefore the command exits. Codex therefore sees the current skillset on its\nfirst launch instead of requiring a second restart. Prism rechecks the same\nsnapshot at MCP startup, session load, and every five minutes—skill delivery\nnever depends on a host lifecycle hook.\n\nOn the first user turn, Prism's native skill, MCP metadata, and managed host\ninstructions request one `session_bootstrap({})` call. Prism then uses the\ndashboard's developer name, Auto-Load Projects, and quick, standard, or deep\nsetting. The response stays focused on greeting and session state because tier\nskills are already present in the host's native skill directory.\n\nHook-free MCP can provide and prioritize that ready-to-display block, but the\nhost model still owns the final assistant message and may summarize it. Prism\ndoes not claim a deterministic verbatim greeting on third-party chat surfaces;\nthat would require a host lifecycle hook, launcher, extension, or Prism-owned\npanel. Context loading itself remains complete even when a host shortens the\nvisible reply.\n\nFree accounts receive only the public hook-free `prism-startup` package; the MCP\nserver still supplies a compact, non-proprietary safety and evidence contract.\nAuthenticated paid accounts receive the protected behavioral and engineering\npackages plus the current subscribed routing set. The paid\n`evidence-first-protocol` keeps ordinary coding lightweight: one correlated\nreproduction is enough to begin an edit, while strict acceptance starts only\nbefore a completion claim, push, or release and inspects only the exact artifacts\nused as proof. Upgrades install newly entitled packages; verified downgrades\nremove only Prism-owned packages while preserving local skills and locally\nmodified conflicts.\n\nWhen upgrading an older Claude Code installation, `prism connect` removes only\nthe exact Prism-owned startup, skill-sync, handoff, and drift hook actions from\nthe legacy bootstrap. It also removes the recognized legacy Prism startup\nsections from `~/CLAUDE.md`, preserves every other instruction, and installs a\nsmall ownership-marked native block that selects `session_bootstrap({})` on the\nfirst turn. User hooks, custom instruction sections, and near matches remain\nuntouched; native skills and server-side reminders preserve those Prism\nfeatures without depending on host lifecycle hooks. On Claude Code and Codex\nconnect additionally registers the prism-route script twice: on every prompt\n(mid-session skill routing) and on `SessionStart` matched to `compact` only\n(post-compaction protected-floor digest). Because hosts expose no native\nsession-end callback, handoff at shutdown is instruction-driven rather than a\nguaranteed lifecycle event.\n\nAfter Claude Code's native user registration succeeds, the same default or\n`--refresh` command checks the nearest `.mcp.json` from the current directory\nthrough the home directory. It removes only the exact legacy\n`prism-mcp` entry `{ \"command\": \"n","github_created_at":"2026-02-12T21:29:53+00:00","created_at":"2026-07-15T11:01:30.660592+00:00","updated_at":"2026-09-20T05:07:57.186022+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"agent-memory","name":"agent-memory"},{"slug":"ai-agent","name":"ai-agent"},{"slug":"cognitive-architecture","name":"cognitive-architecture"},{"slug":"hebbian-learning","name":"hebbian-learning"},{"slug":"hipaa","name":"hipaa"},{"slug":"local-first","name":"local-first"},{"slug":"model-context-protocol","name":"model-context-protocol"},{"slug":"ollama","name":"ollama"}],"trust":{"provenance":{"is_fork":false,"github_id":1156623779,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:07:54.408Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":0,"last_release_at":"2026-07-11T22:44:50Z","stars_delta_30d":2,"open_issues_delta_30d":0},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-08-23T04:00:17.628Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"package.json:@modelcontextprotocol/*","observed_at":"2026-09-20T05:07:55.462Z","server_manifest":true},"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:07:55.462Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-20T05:07:55.462Z","managed_saas":false},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-09-20T05:07:55.462Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T05:07:55.462Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-20T05:07:55.462Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T05:07:55.462Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You need offline AI support for code editing","HIPAA compliance is necessary for your project","Your workflow requires multi-agent coordination and cognitive routing"],"when_not_to_use":["Real-time cloud collaboration features are essential without local fallbacks","Budget constraints prevent subscription to cloud features, which gate higher model capabilities beyond the basic free tier","You prefer lighter-weight tools with no persistent memory infrastructure overhead"],"source":"enrich:decision_facts","observed_at":"2026-07-17T09:03:47.602Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Prism Coder combines local AI assistance with persistent memory for coding tasks across various editors like VS Code."}]}}