Vlk²
Temporal state machine for AI agents that detects and breaks repetitive error loops across languages by fingerprinting errors and injecting preventive constraints, running as an MCP server with SQLite backend.
README
Vlk² — Temporal State Machine for AI Agents
Vlk² gives AI agents a sense of time: what's happening now (PRESENT), what's already been tried (PAST), and what should guide future decisions (FUTURE). It runs as a single binary over MCP, backed by SQLite, and manages these temporal transitions autonomously.
The killer demo: when an agent repeats the same Rust/TS/Python/Go error 3 times, Vlk² auto-archives the loop and injects a preventive constraint so the agent stops retrying the same broken approach. But the architecture is general — the temporal state machine can track any kind of past→present→future transition across any agent framework.
What It Does
- Temporal state machine — each memory has a state: PRESENT (active context), PAST (archived, hidden from context), FUTURE (preventive constraints), PURGED (forgotten). A background agent transitions entries between states without agent intervention.
- Cross-language loop detection — fingerprints errors by language, not by string match. Recognizes Rust (
error[E0277]), TypeScript/JS (TS2345,TypeError), Python (ValueError,KeyError), Go (panic: nil pointer), HTTP (503 Service Unavailable), test frameworks (expected: X, got: Y), with a timestamp-stripping fallback. When the same fingerprint appears ≥3 times, Vlk² auto-archives the loop to PAST and injects a FUTURE constraint. - Reconsolidation on retrieval — every recall checks current beliefs; if contradictory, the memory rewrites itself.
- Token budget enforcement — every 30s, estimates total tokens in PRESENT + FUTURE. If over budget (8K default), archives lowest-importance entries until under budget.
- Autonomous consolidation — background task (30s cycle) evaluates importance, archives stale entries, and forgets disconnected ones.
Why Not Just a Memory System?
General memory systems (agentmemory, Hindsight, Mem0, Supermemory) store facts, preferences, and context. Vlk² does one thing they don't: detect that the same Rust compile error repeated 3 times across different files and inject a constraint so the agent stops retrying the same broken approach. It's not a replacement — it's a specialized fault-detection layer that runs alongside them.
| Capability | Vlk² | agentmemory | Hindsight | Supermemory |
|---|---|---|---|---|
| Fact/persona memory | — | ✅ 53 tools | ✅ hooks | ✅ keywords |
| Cross-language error fingerprinting | ✅ 7 strategies | — | — | — |
| Autonomous loop breaking | ✅ ≥3 repeats auto-archive | — | — | — |
| Reconsolidation on retrieval | ✅ | — | — | — |
| Token-bounded context | ✅ 8K default | — | — | — |
Quick Start
cd vlk-core
cargo build --release
DATABASE_URL="sqlite:vlk.db?mode=rwc" ./target/release/vlk-core
Any MCP client connects via stdin/stdout — JSON-RPC 2.0, one line per message.
MCP Tools
| Tool | Purpose |
|---|---|
vlk_record_state |
Push a log/error as a PRESENT slot for loop detection |
vlk_fetch_context |
Clean context with reconsolidation + loop interception |
vlk_time_travel |
Archive PRESENT → PAST and inject a FUTURE constraint |
vlk_get_history |
Full timeline audit |
vlk_search_memory |
Keyword search across logs and constraints |
vlk_summarize_session |
State counts + token estimates |
vlk_revoke_future |
Remove incorrectly learned constraints |
vlk_get_facts |
Retrieved distilled patterns |
vlk_consolidation_status |
Show consolidation agent state with token bar |
vlk_pin_memory |
Protect a pattern from forgetting |
vlk_unpin_memory |
Restore normal forgetting eligibility |
How Loop Detection Works
- Each error is fingerprinted by type: Rust
error[E...], TSTS..., PythonTypeError:, Gopanic:, HTTP503, test assertion, or first-80-chars fallback - Fingerprints group near-duplicates — same error code with different timestamps/line numbers count as one pattern
- At ≥3 repeats → auto-archives the loop + injects
[SYSTEM ANCHOR]preventive constraint - Future context fetches include the constraint, so the agent stops repeating
Architecture
memory_contents (immutable, team-agnostic)
└── FK ──► agent_timeline (PRESENT / PAST / FUTURE / PURGED)
├── memory_metadata (temporal vectors, importance, connectivity)
└── semantic_facts (distilled patterns from errors)
└── fact_contradictions (resolution tracking)
Consolidation Agent (background tokio, 30s cycle)
SCAN → EVALUATE importance → BUDGET_CHECK → ARCHIVE low-value → FORGET stale
Verification
What's tested: the core loop detection path is verified: 3 identical Rust errors → auto-archive to PAST + FUTURE constraint injection. All 13 MCP tools respond correctly.
Not yet tested: pin/unpin with non-existent timeline_ids, token budget enforcement under load, conflict resolution.
Loop detection smoke test — sends the same Rust error[E0277] 3 times and verifies auto-archive + constraint injection:
import subprocess, json, tempfile, os, sys
db = tempfile.mktemp(suffix='.db')
proc = subprocess.Popen(['./target/release/vlk-core'],
stdin=subprocess.PIPE, stdout=subprocess.PIPE,
stderr=subprocess.DEVNULL,
env={'DATABASE_URL': f'sqlite:{db}?mode=rwc'})
def rpc(msg):
proc.stdin.write((json.dumps(msg) + '\n').encode())
proc.stdin.flush()
return json.loads(proc.stdout.readline())
# Init
rpc({'jsonrpc':'2.0','id':1,'method':'initialize','params':{
'protocolVersion':'2024-11-05','capabilities':{},
'clientInfo':{'name':'test','version':'1.0'}}})
# Send the same Rust error 3 times to trigger loop detection
error = 'error[E0277]: cannot add `str` to `str`'
for i in range(3):
r = rpc({'jsonrpc':'2.0','id':i+2,'method':'tools/call','params':{
'name':'vlk_record_state',
'arguments':{'raw_log': error, 'file_context': f'lib.rs:{i*10}'}}})
assert 'PRESENT state recorded' in r['result']['content'][0]['text']
print(f' Record {i+1}: OK')
# fetch_context triggers loop detection → auto-archive → constraint injection
r = rpc({'jsonrpc':'2.0','id':5,'method':'tools/call','params':{
'name':'vlk_fetch_context','arguments':{}}})
txt = r['result']['content'][0]['text']
assert 'E0277' in txt, 'error missing after fetch'
assert any(kw in txt for kw in ['SYSTEM ANCHOR', 'PREVENTIVE', 'CONSTRAINT']), \
'no constraint injected'
print(f' Fetch: loop archived + constraint injected')
proc.terminate(); proc.wait()
for f in (db, db + '-wal', db + '-shm'):
try:
os.remove(f)
except FileNotFoundError:
pass
print('PASS: loop detection works')
Integration
Add to Hermes, OpenCode, Claude Code, Codex, or any MCP host:
# ~/.hermes/config.yaml or equivalent
mcp_servers:
vlk2:
command: "vlk2"
env:
DATABASE_URL: "sqlite:~/.hermes/vlk/vlk.db?mode=rwc"
timeout: 30
Compatible with any MCP client. Works alongside agentmemory, Hindsight, Supermemory, or Hermes built-in memory.
Requirements
- Rust 2021 edition
- SQLite (bundled via sqlx)
- 6.4MB binary
Current Status
Actively developed. The core loop detection and corrective memory cycle is implemented and E2E-tested. Vlk² is a specialized complement to general memory systems — not a replacement.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。